Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
The evidence library: the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2608.18689v2 Announce Type: replace Abstract: We present Aslema, our system for NADI 2026 Shared Task 5, which consists of two subtasks: intent recognition and slot filling. We evaluate four omni LLMs in a zero-shot setting and compare them with fine-tuned models. Our results show that fine-tuning consistently outperforms zero-shot inference. We further explore synthetic data augmentation by using an LLM to generate culturally grounded Tunisian Derja utterances, followed by voice cloning to generate synthetic speech. Incorporating this synthetic data improves performance on both tasks. Our final submitted system, based on Qwen3-Omni-30B and trained with a mixture of original and synthetic data, achieves 86.8% intent accuracy and 34.7 WER on the devtest split. On the official test set it ranks 1st in slot filling (59.5 CoER) and 4th among 8 teams in intent recognition (66.1% accuracy). We release our experimental scripts and will soon share the synthetic dataset to support further
arXiv:2608.16053v2 Announce Type: replace Abstract: Synthetic conversational speech has become an important resource for developing and evaluating conversational speech systems. However, existing dialogue synthesis pipelines typically generate dialogue content first and then insert interruptions, overlap, and backchannels using handcrafted markers or timing rules, making conversational timing prescribed rather than interaction-driven. We present Agentic-DuplexGen, a dialogue synthesis framework that explicitly decouples content, timing, and acoustics. An LLM first generates the dialogue script, and then two full-duplex conversational models perform the script while listening to each other in real time. This allows conversational timing to emerge naturally while preserving the scripted content. Finally, a high-fidelity text-to-speech model re-renders the interaction without altering its timing. As a demonstration of the proposed framework, we construct a patient--clinician conversationa
arXiv:2608.15763v2 Announce Type: replace Abstract: AI-powered digital avatar streamers must answer product questions, engage viewers, and execute marketing strategies in real time, demanding low latency, frequent strategy updates, and accurate yet effective responses. Evolvable Harnesses, whose Skills, Hooks, prompts, and tools can be updated independently of model weights, enable rapid iteration but expose a trade-off: large models adapt zero-shot yet are too slow, whereas compact models meet latency targets but overfit to fixed Harness configurations. We propose Harness-Aware Training (HAT), which trains compact models to adapt to changing Harnesses. Its key component, Harness-State Augmentation (HSA), applies task-preserving transformations to Skill identifiers and content, tool schemas, prompt structures, and Hook functions. Training proceeds in three stages: HSA-SFT learns reasoning and tool use from strong-model trajectories across diverse environments; General On-Policy Distill
arXiv:2608.05724v2 Announce Type: replace Abstract: We study a specific sparse post-processing pipeline for Random Indexing (RI) on kinship analogies in a small fairytales corpus. The published artifacts use uniform RI context accumulation with 200 dimensions and eight nonzeros, followed by one residual graph average, $\mathbf{E}=(1-\alpha)\mathbf{E}_0+\alpha\mathbf{P}\mathbf{E}_0$, where $\mathbf{P}$ is a row-normalized PPMI graph and $\alpha=0.3$. Terminal row normalization and per-dimension median/IQR scaling are then applied. On the Google analogy benchmark's family section, 272 of 506 questions are valid for every seed. Across five paired seeds, the complete pipeline raises accuracy from 19.41\% to 30.74\%, a gain of 11.32 percentage points with a nested-bootstrap 95\% confidence interval of [6.93, 15.89]. Robust scaling alone contributes 3.24 points [1.25, 5.38], while graph averaging without robust scaling contributes 6.18 points [2.63, 9.92]. A separate 40-question general grid
arXiv:2608.05687v2 Announce Type: replace Abstract: Masked diffusion language models revise many masked output positions in parallel. We call a token committed once it becomes visible and is never masked again, and call a response answer-first when the final answer commits before the reasoning printed ahead of it. On 1,069 GSM8K test questions, an explicit step-by-step instruction increases the accuracy difference between unrestricted decoding and a decoder that permits commitment only near the left-most unresolved position; unrestricted decoding also produces more answer-first trajectories. On MATH-500, the two LLaDA models spend most of a short output canvas on reasoning that commits after the answer, and the benefit of frontier gating decreases as that postanswer writing disappears. Dream-7B has little post-answer writing and follows a different accuracy pattern. A controlled four-option task reserves a one-token answer position before generation. Delaying that position outperforms
arXiv:2608.03446v2 Announce Type: replace Abstract: Multilingual large language models (LLMs) have been shown to perform better on non-English classification tasks when the representations of the given language are more aligned to English within the model. Several cross-lingual alignment (CLA) scores have been proposed for use with LLMs, along with multiple approaches for extracting embeddings from the models. We provide a comparative analysis of 27 CLA score variants, examining how they differ and how well each predicts downstream performance across three tasks. Crucially, while LLMs are widely used for generative tasks such as machine translation, prior work has focused almost exclusively on classification. We therefore investigate whether CLA scores are similarly predictive of translation performance. To enable computing correlations across target languages, we propose a PMI-based translation metric, which is less dependent on the target language and correlates strongly with chrF. W
arXiv:2607.23458v2 Announce Type: replace Abstract: Chain-of-thought (CoT) explanations support oversight only if they are faithful: the stated reasoning must actually produce the answer. Auditing black-box (behavioral) detection of unfaithful CoT against FaithCoT-Bench's human annotations, we find answer correctness structures the problem at every level. Answer incorrectness alone (an oracle diagnostic, not a deployable detector) outperforms every purpose-built signal (AUROC 0.696), because 69% of annotated unfaithfulness occurs on incorrect answers. Stratifying by correctness splits detection into two regimes: on correct answers, behavioral signals moderately separate faithful from post-hoc reasoning (0.63-0.67); on incorrect answers, where most unfaithfulness lives, no tested signal is detectably above chance (replicated on all four models for benchmark-wide signals). The standard step-removal metric anti-correlates with human labels; this inversion reproduces on the benchmark's rel
arXiv:2606.22342v2 Announce Type: replace Abstract: How does research evolve, and can we trace it at the level of individual claims? Scientific progress is not simply a uniform accumulation of facts. Existing citation graphs usually collapse these roles into a single homogeneous edge type, limiting how we can analyze scientific progress. We introduce SciTraj, a typed citation corpus for tracing research evolution across natural language processing, machine learning, and computer vision. SciTraj includes 32,559 papers published between 2015 and 2024 and 573,126 directed edges spanning six research-relation types. Unlike traditional citation graphs, each edge is paired with the claim sentence that motivates its label. Claim-driven relations are verified by natural language inference against their local in-paper context. The corpus further organizes these relations into multi-step typed trajectories that trace how ideas develop across papers and over time. We evaluate the corpus along thr
arXiv:2606.16151v2 Announce Type: replace Abstract: Many reasoning tasks require models to reason over input context, from document-grounded question answering to rule-based deduction. Chain-of-Thought (CoT) prompting produces traces that appear transparent, yet individual steps can silently deviate from the source evidence, even when the final answer is correct. Existing methods detect hallucinations at the response level but fail to identify where in the chain a failure occurs or what type it is. We introduce GRACE, the first human-annotated step-level faithfulness benchmark with a data-driven error taxonomy for context-grounded textual reasoning. GRACE covers CoT traces from 10 models across 4 source datasets, with each step annotated for faithfulness, error category, and natural language explanation. A data-driven taxonomy, discovered bottom-up via unsupervised clustering, organizes failures into two tracks: GRACE-Inference (deductive errors) and GRACE-Grounding (factual grounding
arXiv:2606.13610v2 Announce Type: replace Abstract: Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This creates a new risk: LLM recommenders may consume web content that Generative Engine Optimization (GEO) operators have polluted to mislead them. We ask: to what extent do they become unwitting promoters of fake products? We introduce FORGE (Fake Online Recommendations in Generative Environments), which locally rewrites real products in a frozen set of retrieved web pages into fake ones and measures how often the LLM recommends the fake product, across 225 real products in 15 categories and 5 consumer scenarios. Across 12 commercial and open-weights LLMs, all models are vulnerable: a single polluted page yields fooled rates of up to 27%, while the full top-3 replacement raises this to 73.8%. Vulnerability varies across categories, increasing when models lack stable prior knowledge of the products. Reasoning does not mitigate
arXiv:2606.09590v2 Announce Type: replace Abstract: Medical language models (LMs) can memorize and reproduce protected health information, but privacy evaluations often focus on recovery of training text rather than disclosure under realistic threat models. We introduce a clinically grounded framework that evaluates leakage along a graded axis of adversarial access, ranging from publicly inferable demographics to leaked note fragments. At each tier, we measure verbatim memorization of patient-specific text and semantic leakage of sensitive diagnoses. Applying the framework to an LM continually pretrained on 378k clinical notes, we find that routine encounter metadata (i.e. name, date of birth, visit date, provider name, and practice location) elicits high rates of verbatim memorization across a patient's timeline and sensitive-diagnosis recovery (AUROC 0.91 for abortion, 0.82 for HIV). At the same time, exact-match memorization can overstate disclosure: 36% of memorized tokens reflect
arXiv:2606.04588v2 Announce Type: replace Abstract: Multimodal large language models have made rapid progress in video understanding, yet existing benchmarks largely rely on simple prompts and provide limited evidence about whether models can satisfy explicit output constraints. We introduce VCIFBench, a benchmark for evaluating complex instruction following in video understanding. VCIFBench constructs constraint-rich instructions from both benchmark-adapted and directly video-grounded prompts, covering content, format, style, and structure requirements, and evaluates model outputs with a hybrid verification pipeline. The benchmark contains 306 satisfiable test instructions, 540 DPO training instances, and a 100-item diagnostic set for evaluating whether models can recognize instruction conflicts. Experiments on 10 MLLMs show that joint constraint satisfaction remains challenging. Preference optimization improves instruction following for two model families, while Conflict-100 reveals
arXiv:2605.29708v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) LLMs rely on sparse, router-driven expert activation, yet how safety alignment interacts with routed expert specialization remains underexplored. A common intuition is that safety behavior may be controlled by routing harmful requests to distinct refusal-oriented experts. In this work, we provide empirical evidence for a different picture: routing patterns in aligned MoE LLMs are largely topic-driven, while safety behavior can be altered with little change to the model's intrinsic routing path. Motivated by this observation, we present RASET (Router-Agnostic Safety-Critical Expert Tuning), a red-teaming framework that probes safety enforcement that is localized in a small subset of experts while preserving the model's intrinsic routing behavior. RASET identifies safety-critical experts via a contrastive routing-sensitivity criterion and applies parameter-efficient tuning only to the selected experts, minimizin
arXiv:2605.10488v2 Announce Type: replace Abstract: External knowledge enables large language model (LLM) agents to ground their actions and decisions beyond intrinsic parametric memory in open-ended, knowledge-intensive downstream tasks. Yet the quality of the underlying knowledge bases is systematically limited by incompleteness, incorrectness, or redundancy, manifested as missing evidence or cross-document links, low-confidence or imprecise claims, and ambiguous or coreference resolution issues. Such defects compound under iterative use, degrading retrieval fidelity and downstream task performance. We present \textbf{DeepRefine}, a reinforcement learning framework for agentic knowledge refinement that evolves the quality of any pre-constructed structured knowledge bases, e.g., knowledge graphs or LLM-Wikis, with user queries to make it more suitable for the downstream tasks. DeepRefine performs multi-turn interactions with the knowledge base and conducts abductive diagnosis over the
arXiv:2605.01017v3 Announce Type: replace Abstract: We introduce Xiaohongshu Social Comparison Reader Elicitation (XHS-SCoRE), a reader-grounded benchmark for detecting whether text-only Xiaohongshu (RedNote) posts elicit Upward, Downward, or Neutral/no clear social comparison from a first-person reader perspective. The task targets a socially meaningful relational, behaviorally real signal not reducible to sentiment. Across prompted LLM classifiers and supervised Chinese encoders, we find a consistent generation-detection mismatch: the signal is textually learnable in-domain, but not robustly accessible to prompt-based classification. Prompted LLM classifiers show stable failures, especially neutralization of comparison-eliciting posts and model-specific directional skew. A controlled pilot shows that LLM-generated Xiaohongshu-style posts can shift perceived standing and comparison-related affect even when prompt-based detection of the same construct remains fragile. XHS-SCoRE contrib
arXiv:2604.20443v3 Announce Type: replace Abstract: We introduce DialToM, an annotated Theory of Mind (ToM) benchmark built from naturalistic human-human dialogues using a multiple-choice evaluation framework. Concurrent with recent work showing a gap between explicit mental-state inference and applied ToM in synthetic settings~\cite{gu2024simpletom}, we establish a stricter \emph{State-Driven Diagnostic Probe} in which models must forecast state-consistent dialogue trajectories solely from isolated mental-state profiles without dialogue context. Our evaluation reveals a systematic reasoning asymmetry -- LLMs excel at inferring mental states (Literal ToM) but struggle to leverage them for social forecasting (Functional ToM). Crucially, a domain expert achieves 100\% accuracy on this task, proving its validity and establishing a stark human-AI capability gap. Further, a teacher-student reasoning injection probe shows that Gemini 3 Pro -- which establishes the leading baseline -- possess
arXiv:2604.13076v4 Announce Type: replace Abstract: We investigate the robustness of value alignment via midtraining with synthetic documents, using animal compassion as a value that is both important in its own right and orthogonal to existing alignment efforts. To evaluate compassionate reasoning, we develop and publicly release Animal Norms In Moral Assessment (ANIMA), a 26-question evaluation spanning 13 ethical dimensions, publicly available as a dataset and Inspect evaluation. On ANIMA, training with 3000 documents achieves 77% compared to 40% for instruction-tuning approaches, with generalization to human compassion and no degradation in standard safety benchmarks or capabilities. However, subsequent unrelated instruction-tuning degrades the intervention, with the advantage disappearing after 5000 samples. Our exploratory results suggest document-based value interventions may require explicit preservation strategies to remain effective through typical training pipelines.
arXiv:2604.05779v2 Announce Type: replace Abstract: While large language models (LLMs) demonstrate strong capabilities across diverse user queries, they still suffer from hallucinations, often arising from knowledge misalignment between pre-training and fine-tuning. To address this misalignment, we reliably estimate a fine-grained, instance-level knowledge score via multi-sampled inference. Using the knowledge score, we scale the learning signal according to the model's existing knowledge, while encouraging explicit "I don't know" responses for out-of-scope queries. Experimental results show that this approach allows the model to explicitly express uncertainty when it lacks knowledge, while maintaining accuracy on questions it can answer. Furthermore, we propose evaluation metrics for uncertainty, showing that accurate discrimination between known and unknown instances consistently improves performance.
arXiv:2604.01993v3 Announce Type: replace Abstract: Multi-hop QA benchmarks often reward Large Language Models (LLMs) for spurious correctness, where models reach correct answers through invalid intermediate reasoning. We propose SAFE, an LLM-as-verifier framework for evidence-grounded multi-hop QA. Rather than judging only the final answer after generation, SAFE verifies reasoning during generation by checking intermediate steps against the provided passages and previous reasoning trajectory. To make this process checkable, SAFE decomposes reasoning into atomic, evidence-grounded units represented with Knowledge Graph (KG) triples. At train-time, SAFE verifies benchmark supervision under KG-grounded constraints and constructs reliable verifier training data. At inference-time, an external verifier checks each generated step, identifies invalid reasoning, and provides correction feedback before errors propagate. Across three multi-hop QA benchmarks, SAFE improves accuracy by 8.8 pp on
arXiv:2603.27530v2 Announce Type: replace Abstract: Bock's 1971 algorithm is an exact primal--dual method for the minimum-cost arborescence problem, but its Algol presentation obscures the interaction of its maintained arrays and label-directed control flow. We provide a self-contained tutorial comprising the original listing, a line-mapped explanation, a circuit-forming three-node example, and a complete trace of Bock's ten-node instance. We also present a structured reformulation that replaces temporary span-label changes with explicit component and trace state. Local tightness and contraction-progress results, together with an operational-correspondence theorem, establish that the reformulation preserves Bock's candidate choices, transfers, and final solution.
arXiv:2603.16459v2 Announce Type: replace Abstract: Diffusion large language models (D-LLMs) have emerged as a promising alternative to auto-regressive models due to their iterative refinement capabilities. However, hallucinations remain a critical issue that hinders their reliability. To detect hallucination responses from model outputs, token-level uncertainty, such as entropy, has been widely used to indicate potential factual errors. Nevertheless, unlike auto-regressive models that generate tokens sequentially, D-LLMs generate fixed-length sequences simultaneously, where only a small subset of tokens is informative for hallucination detection. Thus, aggregating uncertainty over all tokens can be suboptimal. Moreover, the evolution trend of uncertainty throughout the diffusion process can also provide valuable signals, highlighting the necessity of modeling its denoising dynamics for hallucination detection. In this paper, we propose DynHD, which bridges these gaps from both spatial
arXiv:2602.18699v2 Announce Type: replace Abstract: Studies of semantic drift report heterogeneous signals, including embedding displacement, neighbor change, distributional divergence, and recursive trajectory instability, without a shared account that relates them. Semantic Substrate Dynamics Theory (SSDT) treats these signals as observables of one time-indexed substrate, St = (X, dt, Pt), that couples embedding geometry to a local diffusion kernel. The contribution is commensurability with a mechanism layer: the substrate separates within-basin churn from basin crossing, recursion-induced instability, and intervention-order effects, distinctions that a single detection score does not recover. Coarse Ricci curvature functions as a dense structural descriptor of basin and bridge geometry across the graph, and bridge mass, a node-level aggregate of incident negative curvature, functions as a sparse descriptor of the genuine bridge structure that is typically uncommon in embedding graph
arXiv:2602.16469v2 Announce Type: replace Abstract: Machine-translated data is widely used in multilingual NLP, particularly where native text is scarce. However, translated text differs systematically from native text. This phenomenon is known as translationese, and it reflects both traces of the source language and characteristic properties of translation itself. In this paper, we study how training on machine-translated data affects small English language models, focusing on how translationese from different source languages shapes linguistic acceptability judgments and language modeling for different domains. We train models on English text translated from 24 typologically and resource-diverse source languages, enabling a systematic analysis of how source language and corpus properties influence what models learn. Our results show that the source language has a clear impact on model behavior: general perplexity is more driven by the lexical diversity of the translated corpus, but g
arXiv:2602.09555v3 Announce Type: replace Abstract: Recent advances in block diffusion language models have demonstrated competitive performance and strong scalability on reasoning tasks. However, their test-time compute allocation remains largely unexplored, leaving a critical speed-effectiveness trade-off unresolved in long Chain-of-Thought reasoning. To address this, we propose a unified test-time compute allocation framework that introduces adaptivity in both step-wise decoding and blockwise generation. At the decoding level, we propose Bounded Adaptive Confidence Decoding (BACD), a difficulty-aware sampling strategy that dynamically adjusts denoising based on model confidence, accelerating inference while controlling error accumulation. Beyond step-wise adaptivity, we introduce the Think Coarse, Critic Fine (TCCF) paradigm that allocates large block sizes for exploratory thinking and smaller block sizes for precise refinement. To stabilize training under varying block configuratio
arXiv:2602.08793v2 Announce Type: replace Abstract: Column Type Annotation (CTA), which assigns a semantic type to a table column, underpins data integration, cleaning, and search over data lakes. State-of-the-art annotators are pre-trained language models (PLMs) fine-tuned on one particular corpus of tables, i.e., a source data lake, and they degrade sharply once deployed on a new (i.e., target) lake, whose tables and semantic type set both differ. Retraining per lake is prohibitive because it demands large volumes of expert annotations. We recast cross-lake adaptation as a knowledge management problem and make the resulting decomposition explicit: relative to a target annotator, a source annotator holds knowledge that must be discarded (source-specific), realigned and reused (shared), or acquired (target-specific). This decomposition exposes which part of the gap a general-purpose LLM can close and which part only target supervision can. Guided by it, we present LakeHopper, which ada
arXiv:2602.03318v4 Announce Type: replace Abstract: Operations Research (OR) relies on expert-driven modeling--a slow and fragile process ill-suited to novel scenarios. While large language models (LLMs) can automatically translate natural language into optimization models, existing approaches either rely on costly post-training or employ multi-agent frameworks, yet most still lack reliable collaborative error correction and task-specific retrieval, often leading to incorrect outputs. We propose MIRROR (a Multi-agent framework with Iterative adaptive Revision and hierarchical Retrieval for optimization modeling in Operations Research), a fine-tuning-free, end-to-end multi-agent framework that directly translates natural language optimization problems into mathematical models and solver code. MIRROR integrates two core mechanisms: (1) execution-driven iterative adaptive revision for automatic error correction, and (2) hierarchical retrieval to fetch relevant modeling and coding exemplar
arXiv:2602.02824v2 Announce Type: replace Abstract: LLM unlearning aims to remove the influence of undesirable knowledge from pretrained language models, which offers a practical mechanism for addressing safety and privacy concerns. Existing unlearning approaches, such as Gradient Ascent, are prone to catastrophic forgetting. Alignment-based approaches provide an alternative direction, yet their effectiveness is limited by the quality of the reference model. In realistic settings, both methods still require large retention datasets to preserve general knowledge. We propose a principled method that quantifies the target LLM's confidence in undesirable knowledge and uses it to calibrate the model's unlearning gradient updates more precisely. It enables fine-grained control over forgetting while better preserving model utility, thus reducing the dependence on retention data or prohibitive unlearning training data. Extensive evaluations on multiple benchmarks, including MUSE and WMDP, show
arXiv:2602.00612v3 Announce Type: replace Abstract: Diffusion Large Language Models (dLLMs) have demonstrated promising generative capabilities and are increasingly used to produce formal languages defined by context-free grammars, such as source code and chemical expressions. However, as probabilistic models, they still struggle to generate syntactically valid outputs reliably. A natural and promising direction to address this issue is to adapt constrained decoding techniques to enforce grammatical correctness during generation. However, applying these techniques faces two primary obstacles. On the one hand, the non-autoregressive nature of dLLMs renders most existing constrained decoding approaches inapplicable. On the other hand, current approaches specifically designed for dLLMs may allow intermediate outputs that are impossible to complete into valid sentences, which significantly limits their reliability in practice. To address these challenges, we present LAVE, a constrained dec
arXiv:2601.23182v2 Announce Type: replace Abstract: Despite the non-autoregressive potential of diffusion language models (dLLMs), existing decoding strategies demonstrate positional bias, failing to fully unlock the potential of arbitrary generation. In this work, we delve into the inherent spectral characteristics of dLLMs and present the first frequency-domain analysis showing that low-frequency components in hidden states primarily encode global structural information and long-range dependencies, while high-frequency components are responsible for characterizing local details. Based on this observation, we propose FourierSampler, which leverages a frequency-domain sliding window mechanism to dynamically guide the model to achieve a "structure-to-detail" generation. FourierSampler outperforms other inference enhancement strategies on LLADA and SDAR, achieving relative improvements of 20.4% on LLaDA1.5-8B and 16.0% on LLaDA-8B-Instruct. It notably surpasses similarly sized autoregres
arXiv:2601.17609v3 Announce Type: replace Abstract: In domains like medicine and finance, large-scale labeled data is costly and often unavailable, leading to models trained on small datasets that struggle to generalize to real-world populations. Large language models contain extensive knowledge from years of research across these domains. We propose LoID (Logit-Informed Distributions), a deterministic method for extracting informative prior distributions for Bayesian logistic regression by directly accessing their token-level predictions. Rather than relying on generated text, we probe the model's confidence in opposing semantic directions (positive vs. negative impact) through carefully constructed sentences. By measuring how consistently the LLM favors one direction across diverse phrasings, we extract the strength and reliability of the model's belief about each feature's influence. We evaluate LoID on ten real-world tabular datasets under synthetic out-of-distribution (OOD) settin
arXiv:2601.16890v2 Announce Type: replace Abstract: Automated fact-checking (AFC) systems are susceptible to adversarial attacks, enabling false claims to evade detection. Existing adversarial frameworks typically rely on injecting noise or altering semantics, yet no existing framework exploits the adversarial potential of persuasion techniques against AFC systems, which are widely used in disinformation campaigns to manipulate audiences. In this paper, we introduce a novel class of persuasive adversarial attacks on AFCs by employing an LLM to rephrase claims using persuasion techniques. Considering $15$ techniques grouped into $5$ categories, we study the effects of persuasion on both claim verification and evidence retrieval using a decoupled evaluation strategy. Experiments on the FEVER and FEVEROUS benchmarks show that persuasion attacks can substantially degrade both verification performance and evidence retrieval. Our analysis identifies persuasion techniques as a potent class of
arXiv:2601.09716v2 Announce Type: replace Abstract: Natural Language Processing (NLP) is rapidly transforming research methodologies across disciplines, yet African languages remain largely underrepresented in this technological shift. This paper provides the first comprehensive overview of NLP progress and challenges for the six national languages officially recognized by the Senegalese Constitution: Wolof, Pulaar, S\'er\`ere, Diola, Mandingue, and Sonink\'e. We synthesize linguistic, socio-technical, and infrastructural factors that shape their digital readiness and identify gaps in data, tools, and benchmarks. Building on existing initiatives and research works, we analyze ongoing efforts in various tasks, covering both text and speech modalities. We also provide a centralized GitHub repository that compiles publicly accessible resources for a range of NLP tasks across these languages, designed to facilitate collaboration and reproducibility. A special focus is devoted to the applic
arXiv:2601.05882v2 Announce Type: replace Abstract: Preference tuning aligns base language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather than likelihood alone. Prior work has shown that preference tuning degrades performance and reduces helpfulness outside the training domain. However, the extent to which adaptation strategies mitigate this domain shift remains unexplored. We address this challenge by conducting a comprehensive and systematic study of alignment generalization under domain shift. We compare five popular alignment objectives and various adaptation strategies from source to target, including target-domain supervised fine-tuning and pseudo-labeling, across summarization, question-answering helpfulness, and safety alignment tasks. Our findings reveal systematic differences in generalization across alignment objectives under domain shift. We show that adaptation strategies based on pseudo-labeling substanti
arXiv:2510.11358v3 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) is typically optimized for topical relevance, yet its success ultimately depends on whether retrieved passages are useful for a large language model (LLM) to generate correct and complete answers. We argue that such utility is often LLM-specific rather than universal, due to differences in models' knowledge, reasoning, and ability to leverage evidence. We formalize LLM-specific utility as the performance improvement of a target LLM when a passage is provided, compared to answering without evidence. To systematically study LLM-specific utility, we construct a benchmark of LLM-specific gold utilitarian passages for four LLMs (Qwen3-8B/14B/32B and Llama 3.1-8B) on three QA datasets (Natural Questions, TriviaQA, and MS MARCO-FQA). Our analysis shows that utilitarian passages are model-dependent and non-transferable: each LLM performs best with its own utilitarian evidence, while evidence optimized for
arXiv:2510.03536v3 Announce Type: replace Abstract: Multi-turn medical question answering (QA) aims to model realistic clinical diagnosis, where a doctor gathers patient information across multiple turns of conversation. Existing multi-turn medical conversation systems have shown promising progress, but they often rely on accumulated conversation histories as memory, leaving clinical evidence fragmented across turns. We propose GraphMed-LT, a patient-specific graph memory approach with latent clinical thought refinement for multi-turn medical conversations. GraphMed-LT extracts patient-specific clinical triplets from patient responses, retrieves relevant knowledge triplets, and organises them into an incrementally updated graph memory. The graph memory is projected into graph-conditioned evidence tokens and refined inside a trainable doctor agent through hidden-state feedback, enabling the agent to update its internal clinical context before asking follow-up questions or producing the
arXiv:2510.01028v2 Announce Type: replace Abstract: Large language models have made revolutionary progress in generating human-like text, yet their outputs often tend to be generic, exhibiting insufficient structural diversity, which limits personalized expression. Recent advances in diffusion models have opened new opportunities for improving language generation beyond the limitations of autoregressive paradigms. In this work, we propose a syntax-guided diffusion language model that integrates structural supervision and personalized conditioning to enhance text quality, diversity, and controllability. We introduce a cascaded framework that generates syntactic guidance before conditional text generation, and further generalize it to a novel noncascaded architecture for better alignment between structure and content. By incorporating syntactic information in the generating process, the proposed model better captures the lexical and structural characteristics of stylistic sentence constr
arXiv:2509.12811v2 Announce Type: replace Abstract: Large Language Models (LLMs) have shown remarkable prowess in text generation, yet producing long-form, factual documents grounded in extensive external knowledge bases remains a significant challenge. Existing "top-down" methods, which first generate a hypothesis or outline and then retrieve evidence, often suffer from a disconnect between the model's plan and the available knowledge, leading to content fragmentation and factual inaccuracies. To address these limitations, we propose a novel "bottom-up," data-driven framework that inverts the conventional generation pipeline. Our approach is predicated on a "Retrieval-First for Knowledge, Clustering for Structure" strategy, which first establishes the "knowledge boundaries" of the source corpus before any generative planning occurs. Specifically, we perform exhaustive iterative retrieval from the knowledge base and then employ an unsupervised clustering algorithm to organize the retri
arXiv:2508.13533v2 Announce Type: replace Abstract: Within a model family, a smaller variant is often deployed as a drop-in replacement for a larger one when their performance is similar. However, performance alone does not tell the full story. We propose a framework to evaluate trust-equivalence between a larger model and a smaller one in the same family along two dimensions. The first is attribution alignment: do both models base their predictions on the same input features? The second is calibration similarity: do both models share the same relationship between confidence and accuracy? We evaluate the Llama-2 family on two text classification tasks: Natural Language Inference and Paraphrase Identification. Attribution alignment is measured using two well-known methods: LIME and SHAP. Agreement between model pairs is quantified via the Jaccard coefficient over top-K attributed features. We observe that attribution alignment between models is generally low, indicating that smaller and
arXiv:2508.07173v3 Announce Type: replace Abstract: Omni-modal Large Language Models (OLLMs) that integrate visual, auditory, and textual processing face severe safety risks. They exhibit fragile defenses against audio-visual joint harmful inputs and demonstrate inconsistent safety performance across different modalities, enabling simple modality-switching jailbreaks. However, existing safety benchmarks fail to comprehensively assess these risks due to the absence of audio-visual joint samples, limited modality coverage, and lack of parallel test cases for cross-modal consistency evaluation. To address these gaps, we introduce Omni-SafetyBench, the first comprehensive parallel benchmark for OLLM safety evaluation, featuring 23,328 test instances across 24 modality variations derived from 972 seed samples. Recognizing that complex inputs pose comprehension challenges and that cross-modal consistency is critical for OLLM safety, we propose tailored metrics: a Safety-score based on Condit
arXiv:2508.05078v2 Announce Type: replace Abstract: Parameter-Efficient Fine-Tuning (PEFT) is essential for adapting Large Language Models (LLMs) to multi-task scenarios. A prevailing trend in this field involves complex LoRA variants with multiple adapters or heads, which rely on the premise that architectural isolation of task-specific knowledge is necessary. However, this design often introduces dynamic routing, preventing weight merging and causing significant inference latency. In this work, we present a direct challenge to this paradigm. We first reveal a paradox where a simplified, router-free multi-head model with high inter-head redundancy outperforms complex, diversity-driven baselines. Furthermore, we demonstrate that a unified, single-adapter LoRA with increased rank achieves highly competitive performance, questioning the necessity of multi-component structures. Based on these findings, we propose Align-LoRA, a unified and efficient framework that shifts the focus from arc
arXiv:2507.18061v4 Announce Type: replace Abstract: Spoken Language Models (SLMs) are expected to support natural spoken interaction beyond task completion. However, existing SLM benchmarks primarily evaluate semantic correctness in structured settings and provide limited assessment of interactional behavior grounded in acoustic context. To address this gap, we introduce TELEVAL, a large-scale SLM benchmark for Chinese spoken interaction in instruction-free, audio-conditioned settings. TELEVAL evaluates two complementary aspects: (1) Reliable Content Fulfillment, which measures semantic accuracy of SLMs under diverse acoustic and linguistic conditions, and (2) Interactional Appropriateness, which assesses whether models produce natural and appropriate responses by implicitly grounding behavior in auditory cues. Experiments show that while models perform competitively on semantic tasks, their performance degrades under acoustic variability and in interactional settings. We observe consi
arXiv:2507.12295v2 Announce Type: replace Abstract: Text anomaly detection is a critical task in natural language processing (NLP), with applications spanning fraud detection, misinformation identification, spam detection and content moderation, etc. Despite significant advances in large language models (LLMs) and anomaly detection algorithms, the absence of standardized and comprehensive benchmarks for evaluating the existing anomaly detection methods on text data limits rigorous comparison and development of innovative approaches. This work performs a comprehensive empirical study and introduces a benchmark for text anomaly detection, leveraging embeddings from diverse pre-trained language models across a wide array of text datasets. Our work systematically evaluates the effectiveness of embedding-based text anomaly detection by incorporating (1) early language models (GloVe, BERT); (2) multiple LLMs (LLaMA-2, LLaMA-3, Mistral, OpenAI embedding models (small, ada, large)); (3) multi-
arXiv:2506.20073v2 Announce Type: replace Abstract: Spatio-temporal data mining plays a pivotal role in informed decision making across diverse domains. However, existing models are often restricted to narrow tasks, lacking the capacity for multi-task inference and complex long-form reasoning that requires generation of in-depth, explanatory outputs. These limitations restrict their applicability to real-world, multi-faceted decision scenarios. In this work, we introduce STReason, a novel framework that integrates the reasoning strengths of large language models (LLMs) with the analytical capabilities of spatio-temporal models for multi-task inference and execution. Without task-specific fine-tuning, STReason leverages in-context learning to decompose complex natural language queries into modular, interpretable programs, which are then systematically executed to generate both numerical solutions and detailed reasoning rationales. By grounding all explanations in verified computational
arXiv:2506.18919v5 Announce Type: replace Abstract: As a multimodal communication medium that integrates images and text, memes often convey implicit harmful content through metaphors, satire, and humor, making harmful meme detection a complex and challenging task. Although recent studies have achieved considerable progress in detection accuracy and model interpretability, large-scale, high-quality datasets for harmful memes remain scarce. Moreover, existing methods still exhibit notable limitations in identifying implicit risks and understanding fine-grained semantics. To address these challenges, we construct MemeMind, a large-scale dataset for harmful meme detection. MemeMind comprises a broad collection of publicly available memes and adopts a rigorous and comprehensive taxonomy of harmful content developed in accordance with widely recognized international standards and contemporary Internet contexts. In addition, the dataset provides detailed structured Chain-of-Thought (CoT) rea
arXiv:2506.07356v3 Announce Type: replace Abstract: While Finetuning-as-a-Service (FaaS) enables customization of Large Language Models (LLMs) using user data, this service is vulnerable to safety degradation when user data includes harmful prompts, a threat known as harmful finetuning attacks. To defend against this, prior work first constructs safety-aligned LLM and then finetunes the LLM on user data. However, we observe that the safety-aligned weights provide weak initialization for downstream task learning, leading to suboptimal safety and utility. Motivated by this limitation, we shift the safe FaaS finetuning paradigm from finetuning safety-aligned weights to finetuning base weights under explicit safety-teacher guidance. Specifically, we propose a Refusal-Teacher (Ref-Teacher)-guided finetuning framework. Our approach directly finetunes the base LLM under the guidance of a safety-aligned Ref-Teacher, which filters harmful prompts from user data and distills safety into the base
arXiv:2505.17571v2 Announce Type: replace Abstract: Personalization is a critical task in modern intelligent systems, with applications spanning diverse domains, including interactions with large language models (LLMs). Recent advances in reasoning capabilities have significantly enhanced LLMs, enabling unprecedented performance in tasks such as mathematics and coding. However, their potential for personalization tasks remains underexplored. In this paper, we present the first systematic evaluation of large reasoning models (LRMs) for personalization tasks. Surprisingly, despite generating more tokens, LRMs do not consistently outperform general-purpose LLMs, especially in retrieval-intensive scenarios where their advantages diminish. Our analysis identifies three key limitations: divergent thinking, misalignment of response formats, and ineffective use of retrieved information. To address these challenges, we propose Reinforced Reasoning for Personalization (\model), a novel framework
arXiv:2504.09421v3 Announce Type: replace Abstract: Recent advances in reasoning with large language models (LLMs)has shown remarkable reasoning capabilities in domains such as mathematics and coding, yet their application to clinical diagnosis remains underexplored. Here, we introduce ClinicalGPT-R1, a reasoning enhanced generalist large language model for disease diagnosis. Trained on a dataset of 20,000 real-world clinical records, ClinicalGPT-R1 leverages diverse training strategies to enhance diagnostic reasoning. To benchmark performance, we curated MedBench-Hard, a challenging dataset spanning seven major medical specialties and representative diseases. Experimental results demonstrate that ClinicalGPT-R1 outperforms GPT-4o in Chinese diagnostic tasks and achieves comparable performance to GPT-4 in English settings. This comparative study effectively validates the superior performance of ClinicalGPT-R1 in disease diagnosis tasks. Resources are available at https://github.com/med
arXiv:2503.14900v2 Announce Type: replace Abstract: The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like languages. Large language models achieve success by being trained on vast amounts of textual data, including online sources with copyrighted content and user-generated knowledge. However, this comes at a cost: the potential risk of exposing users' privacy and violating copyright protections. Thus, to safeguard individuals' "right to be forgotten", there has been increasing interests in machine unlearning -- the process of removing information carried by particular training samples from a model while not deteriorating its predictive quality. This is a challenging task due to the black-box nature of language models. Most existing studies focus on mitigating the impact of those forgot samples upon a model's outputs, and do not explicitly consider the geometric distribu
arXiv:2502.14643v3 Announce Type: replace Abstract: Direct Preference Optimization (DPO) is a widely adopted offline algorithm for preference-based reinforcement learning from human feedback (RLHF), designed to improve training simplicity and stability by redefining reward functions. However, DPO is hindered by several limitations, including length bias, memory inefficiency, and probability degradation. To address these challenges, we propose Length-Controlled Margin-Based Preference Optimization (LMPO), a more efficient and robust alternative. LMPO introduces a uniform reference model as an upper bound for the DPO loss, enabling a more accurate approximation of the original optimization objective. Additionally, an average log-probability optimization strategy is employed to minimize discrepancies between training and inference phases. A key innovation of LMPO lies in its Length-Controlled Margin-Based loss function, integrated within the Bradley-Terry framework. This loss function reg
arXiv:2412.06769v4 Announce Type: replace Abstract: Large language models (LLMs) are typically constrained to reason in the language space, where they express the reasoning process through a chain-of-thought (CoT) to solve complex problems. However, the language space may not always be optimal for reasoning. Most word tokens primarily ensure textual coherence and are not essential for reasoning, while some critical tokens require complex planning and pose challenges to LLMs. To explore the potential of reasoning beyond language, we introduce a new paradigm called Coconut (Chain of Continuous Thought). Coconut utilizes the last hidden state of the LLM as a representation of the reasoning state, termed "continuous thought." Instead of decoding this state into words, we feed it back to the model as the next input embedding directly in the continuous space. This latent reasoning paradigm enables an advanced reasoning pattern, where continuous thoughts can encode multiple alternative next s