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:2608.20831v1 Announce Type: new Abstract: Aspect-based sentiment analysis (ABSA) quadruple extraction requires jointly predicting target, aspect, opinion, and sentiment over reviews that often contain multiple fine-grained sentiment tuples. While large chain-of-thought (CoT) models perform well on this task, distilling them into smaller deployable models remains difficult. We identify a task-specific failure mode in distilled ABSA extraction: student errors at the target-aspect interface create structurally invalid states, such as broken target-aspect bindings and hallucinated targets, which then corrupt downstream predictions. Conventional off-policy distillation is poorly suited to this setting because it trains only on teacher-generated trajectories and provides little supervision on the student-induced structural states that dominate inference. To address this mismatch, we propose STAR-OPD (STructured Aspect-cascade-aware On-Policy Reward Distillation), which builds on generi
arXiv:2608.20804v1 Announce Type: new Abstract: Temporal Knowledge Graph (TKG) extrapolation seeks to infer future facts from time-varying relational histories. Recent diffusion-based approaches improve uncertainty modeling through generative denoising, but their aggregated conditioning on subject histories may insufficiently distinguish query-specific evidence from non-salient historical facts, thereby diluting target-discriminative signals. To bridge this gap, we propose FreqDiff, a Frequency-aware Diffusion framework for TKG extrapolation. Specifically, FreqDiff formulates future object prediction as query-slot denoising and develops a dual-stream denoiser that integrates temporal dependency modeling with context-aware spectral calibration. The spectral branch synthesizes history-conditioned filters from learnable bases to adaptively re-calibrate denoising representations, while a frequency-domain regularizer is proposed to align the denoised target with the gold object in spectral
arXiv:2608.20777v1 Announce Type: new Abstract: As scientific literature grows and papers increasingly under-report limitations, multi-agent LLMs offer a promising approach to systematically uncover these hidden failure modes. Here, we introduce Tree-of-Concerns, a multi-agent framework that deploys specialized skeptic personas, each operating through a category-specific analytical lens, as parallel debate trees to extract unstated limitations from scientific papers. Each persona conducts structured, evidence-grounded argumentation, while a Panel Review mechanism re-evaluates each surviving claim from all five perspectives to correct category drift and severity miscalibration. Through experiments on ToC-Bench, our benchmark of 414 research papers with 1,905 unstated limitations, sourced from reviewer-reported weaknesses and follow-up citation critiques, we demonstrate that ToC improves precision by 79% and coverage by 11% relative to strongest baselines, surfacing specific, evidence-gr
arXiv:2608.20757v1 Announce Type: new Abstract: We describe the PSK submission to the WMT 2026 Multilingual Instruction Shared Task. Our system uses the 3.35B-parameter Tiny Aya Global model with three QLoRA adapters, one for each task. The adapters are trained on multilingual document-summary pairs, passage-based question answering, and filtered standalone question answering. The summarization data also includes scientific papers with their author-written abstracts. On our held-out split, the context and summarization adapters perform better than our multitask adapter, which was trained only on data supplied by the organizers. Results for open QA are mixed and vary with answer length and evaluation method. We therefore submit three systems with the same context and summarization adapters but different open-QA adapters.
arXiv:2608.20711v1 Announce Type: new Abstract: High-performance ML systems increasingly rely on GPU kernels whose editable source is unavailable, generated, or too distant from final machine code to expose remaining optimizations. Existing LLM kernel optimizers and autotuners mainly operate on CUDA, Triton, HIP, or tensor-program source and validate against reference implementations. We study a stricter setting: optimizing an already compiled AMDGPU code object, where the deployed binary is the only behavioral oracle. We present AsmEvo, an agentic assembly-level optimizer for AMD GPU kernels. Given an AMDGPU code object K0, AsmEvo reconstructs a reassemblable representation, proposes low-level edits with a long-horizon agent, rebuilds an ABI-preserving optimized object, and accepts candidates only after differential verification against K0 under identical launches. AsmEvo combines code-object recovery, metadata-aware rebuilding, profiling-guided hot-window editing, correctness-gated t
arXiv:2608.20647v1 Announce Type: new Abstract: Splitting a bidirectional LSTM's contextual representation into a forward-only $F_i$ (strictly a function of tokens $1..i$) and a backward-only $B_i$ (strictly a function of tokens $i..n$) beats either alone and beats a fused self-attention representation for dependency relation-type classification. But a specific, natural extension of this idea -- pairing a token's forward state against a \emph{candidate}'s backward state (``cross-direction'' pairing, $F_i$ vs.\ $B_j$) -- consistently \emph{underperforms} same-direction pairing, and the penalty \emph{grows}, not shrinks, with token distance, both paired-bootstrap significant. We diagnose why using a frozen-trunk methodology: architectural information leakage between directions is impossible by construction (a single-layer BiLSTM, verified by code inspection); 93\% of the same-vs-cross gap survives freezing the trunk and training only fresh heads, ruling out training-co-adaptation as the
arXiv:2608.20636v1 Announce Type: new Abstract: Many text classification decisions are viable based on constituent excerpts alone. Taking inspiration from the field of multiple instance learning, we present an algorithm for training a neural network to classify text by selecting such excerpts. We show that our approach is also scalable with demonstrated learning against samples with nearly 1M tokens. We evaluate our methods on 7 datasets with emphasis on long-textual collections that far exceed the encoding limit of our base model. We present state-of-the-art results with this algorithm on 3 datasets: identification of political bias in news outlets, trigger warnings in long stories, and demographic characteristics of authors in tweet collections. Furthermore, the model trained on weakly-labeled collections of text (bags) generalizes to accurately classify constituent, smaller instances. Besides a new state-of-the-art for these problems, this approach is one of the few neural methods t
arXiv:2608.20634v1 Announce Type: new Abstract: Agents learn to act through interaction with environments, yet the environments used for training are often manually constructed or synthesized around predefined tasks and benchmarks. This task-centric paradigm makes it difficult to scale environments that reflect realistic and evolving workflows where diverse tasks can naturally emerge from the underlying world. We introduce AgentMercury, a scalable framework for synthesizing executable environments from high-level business scenarios. Rather than constructing an environment for a specific task, AgentMercury first instantiates a persistent world with entities, services, tools, state, and executable cross-service invariants, from which diverse tasks and interaction trajectories can subsequently emerge. We construct 4,783 executable environments spanning 14 industries and 50 countries, and use them as training substrates for reinforcement learning. Despite being generated without targeting
arXiv:2608.20632v1 Announce Type: new Abstract: Efficient-transformer research often motivates token pruning and adaptive computation with the claim that not all tokens require equal computational effort. We test this claim end to end using SEWN, a two-stream Transformer that routes tokens through either lightweight or full-capacity processing using a learned gate. Across our experiments, routing introduces negligible accuracy change relative to parameter-matched baselines, while the gate's token-importance signal depends critically on how it is learned. A static lexicon-seeded prior fails a counterfactual faithfulness test on BoolQ, whereas a fully contextual gate achieves highly significant separation ($p<10^{-10}$) on both evaluated tasks without changing task accuracy.
arXiv:2608.20627v1 Announce Type: new Abstract: Agentic retrieval-augmented generation (RAG) interleaves retrieval, reasoning, and answer generation across multiple hops. A retrieval error at hop 1 can surface only as a wrong answer at hop 3, while later retrieval can also repair the trajectory. This paper introduces AgenticRAG-FP, an interventional benchmark for causal failure attribution in agentic RAG. The benchmark injects a certified fault at a specified hop, re-executes the downstream trajectory, and evaluates diagnosers against the known intervention. Its central question is whether a post-hoc trace still identifies the injected hop after the suffix changes. In the completed strict dense Claude Haiku 4.5 sweep on 80 three-hop MuSiQue questions, coverage-based diagnosis is 0.91 at hop 1 and 0.00 at hops 2 and 3 (n=43,36,21 failed trajectories). A smaller content-corruption study changes an answer-bearing or bridge fact in topically intact evidence. At depth 2, where 18 failed cas
arXiv:2608.20607v1 Announce Type: new Abstract: Panels of inexpensive LLM judges increasingly make accept-or-escalate decisions. In factuality settings, accepting a claim because several reference-free judges agree can create a hidden risk: agreement may reflect shared false-negative blind spots rather than independent evidence. We introduce JuryProbe, an empirical consensus-risk diagnostic for reference-free factuality judge panels, paired with a calibration-based routing policy. JuryProbe estimates consensus risk from a labeled calibration probe using false-negative-only (FN-only) judge correlation and false-consensus lift; when flagged high-risk, reference-free majority accepts are routed to the same judges with trusted references. On audited FEVER corruptions, reference-free panels show correlated false negatives (FN-only correlations 0.402 and 0.368; lifts 3.13x and 18.13x), while unanimous false consensus drops to zero under a trusted-reference best-case diagnostic on both minima
arXiv:2608.20530v1 Announce Type: new Abstract: Speculative decoding accelerates language-model inference by drafting future tokens that the target model verifies in parallel. A diffusion-style block head such as DFlash is an attractive drafter, predicting an entire block of future tokens in one forward pass. However, it is trained on per-position marginals rather than the joint block distribution, so the tokens it emits are individually plausible yet jointly incoherent. We introduce LiLiCorr, a Lightweight Likelihood-based model that Correlates the per-position marginal distributions a drafter already produces. It keeps the top-k tokens at each position as candidates and processes them jointly, producing for each an in and an out vector. A pair of adjacent candidates matches when the earlier one's out vector has high cosine similarity with the later one's in vector. These matches capture the block's joint structure without ever materializing the full joint distribution. One lightweigh
arXiv:2608.20405v1 Announce Type: new Abstract: Persuasive argument generation requires modeling audience beliefs, rhetorical strategies, and factual grounding. Despite recent advancements, existing methods remain largely audience-agnostic and fail to integrate strategy selection to improve persuasiveness. To bridge this gap, we propose Argus, an agent-based framework that operationalizes classical rhetoric for persuasive writing. At its core, a Theory-of-Mind (ToM) Reasoner constructs an explicit dual mental model of the audience's beliefs and values to guide downstream decisions. This representation conditions a component-aware planner that decomposes the argument into subtopics, assigns fine-grained rhetorical functions (logos, pathos, ethos, kairos), and triggers strategy-guided evidence retrieval at planning time. Finally, a refinement module iteratively targets and resolves multi-dimensional weaknesses without quality regression. We evaluate Argus across three diverse benchmarks
arXiv:2608.20402v1 Announce Type: new Abstract: Biomedical knowledge graphs (KGs) are pivotal for knowledge organization, yet traditional binary relations often struggle to represent the conditional nature of biomedical knowledge. Symptoms provide a shared phenotypic layer for linking Traditional Chinese Medicine (TCM), which relies on symptom patterns for syndrome differentiation and treatment selection, with modern biomedicine, which connects clinical manifestations to diseases and molecular mechanisms. We present LingShu, a large-scale symptom-centric contextualized knowledge graph designed to bridge TCM and modern biomedicine. The exported version of LingShu analyzed in this study comprises 17.33 million atom-level entity records and 39.47 million relation records, including 17.19 million semantic triples and 22.29 million contextualized quadruples. LingShu integrates multi-source data, including clinical electronic medical records, authoritative TCM texts, biomedical ontologies, a
arXiv:2608.20396v1 Announce Type: new Abstract: Language development is characterized by a gradual convergence of children's speech toward adult patterns. Measuring this process has traditionally required detailed transcription and language-specific expertise, limiting scalability across languages and populations. Here, we use speech embeddings to capture this convergence directly from the acoustic signal in longform, child-centered recordings, taken as children go about their daily lives. Using HuBERT-BASE, we extracted embeddings from speech vocalizations of children who are deaf/hard-of-hearing and their female adult caregivers ($>$925 hrs. observation). Embedding distance between children and caregivers decreased with hearing age, controlling for pitch and vocalization length, indicating, as expected, that children's speech patterns converge to caregivers over development. This single distance metric likewise related to multiple standardized measures of speech and language from inf
arXiv:2608.20393v1 Announce Type: new Abstract: Agentic large language models (LLMs) deployed in fact-sensitive applications such as customer support must simultaneously preserve factual correctness and generate responses in a controllable stylistic register. Activation steering enables fine-tuning-free style control by perturbing hidden representations, but it lacks an explicit mechanism for distinguishing verifiable facts from stylistic content, leading to semantic leakage. We address this challenge through \emph{Defactualize-Steer-Rehydrate} (DSR), a knowledge-engineering framework that integrates a typed, salience-weighted knowledge graph (KG) with activation steering. DSR extracts salient entities using a layered regex or NER or lexical-classifier pipeline, replaces them with typed placeholders prior to steering, and deterministically restores verified values through salience-guided rehydration after generation. DSR is evaluated across six LLaMA-family models (1B--13B parameters)
arXiv:2608.20392v1 Announce Type: new Abstract: LLM-powered meeting assistants are deployed at scale, yet systematic evaluation of their grounding fidelity remains limited to static benchmarks that miss failure modes tied to specific discourse structures or reasoning demands. We propose Evaluation-as-Search (EaS), a feedback-driven methodology that frames quality evaluation as an adaptive search over the space of natural questions a meeting participant might ask. Rather than sampling uniformly, EaS learns from evaluator feedback across iterations to concentrate probing effort on cognitive demands where failures are most likely, guided by a UCB-scored coverage map and blind multi-dimensional quality evaluation. Using EaS, we construct MeetingProbe, a benchmark of over $3{,}000$ annotated question--answer pairs spanning 20 transcripts from three meeting genres and three LLM assistants. In ablations, adaptive search surfaces $2.5\times$ more failures than random probing ($7.1\%$ vs. $2.9\
arXiv:2608.20391v1 Announce Type: new Abstract: Most legal NLP resources draw from federal case law and focus on coarse classification, leaving administrative adjudication, where the vast majority of government decisions occur, essentially unaddressed. We introduce ImmigrationReason, a large-scale structured dataset derived from 12,375 non-precedent decisions of the U.S. Citizenship and Immigration Services (USCIS) Administrative Appeals Office (AAO) spanning 2005 to 2026. Each record captures the applicable legal framework, per-criterion evidence-sufficiency findings under a five-category label, verbatim adjudicator-criticism quotes, all citations, and final dispositions, alongside high-quality Claude-transcribed source text. Extraction quality is validated through a three-pass pipeline combining two independent modalities with comparison-prompt adjudication by Opus 4.7, and verified by domain experts on a 500-record sample. The dataset documents nearly 9,000 verbatim instances of AAO
arXiv:2608.20388v1 Announce Type: new Abstract: Microservice placement in the compute continuum is driven by low-level Service-level Objectives (SLOs), but requiring users to specify metric-level constraints creates an adoption barrier and increases misconfiguration risk. Although large language models (LLMs) can interpret natural-language intents, direct generation of orchestration-consumable SLO artifacts remains unreliable due to unsupported constraints, incorrect grounded values, and schema violations. These errors can propagate to downstream placement logic and produce infeasible or incorrect placements. This paper presents Intent Engine, a natural-language intent translation architecture that constructs validated SLO artifacts for compute-continuum service placement. Intent Engine acts as an intent acquisition and SLO construction layer for existing intent-driven orchestration and placement frameworks; it does not perform placement or runtime QoS optimization. The architecture co
arXiv:2608.20387v1 Announce Type: new Abstract: While recent text-to-speech (TTS) models achieve high naturalness, controlling fine-grained expression via natural-language instructions remains challenging. We introduce Poly- InstructTTS, which learns expressive speech from open-ended instructions using in-the-wild audiovisual data. We build a scalable multi-modal pipeline to construct a 1,000-hour instruction-annotated corpus covering 1,000+ fine-grained emotions and styles. The framework uses a prompt-free GPT with attribute-based thinking tokens, followed by a flow-matching module that injects timbre from a reference audio. We also present a speaker fine-tuning procedure to transfer instruction control to specific speakers while preserving persona. We further extend InstructTTSEval with broader tasks. Experiments show that Poly-InstructTTS delivers strong performance in instruction adherence and expressiveness. Audio demos and the expanded testset are available on our project page.
arXiv:2608.20385v1 Announce Type: new Abstract: Systematic reviews rely on quality appraisal of included studies, a process that is time-consuming and sensitive to ambiguity in checklist criteria. Although large language models (LLMs) offer opportunities to support these tasks, appraisal checklists are typically treated as fixed inputs, and it remains unclear how their design affects agreement with expert judgments. Therefore, we investigate (1) whether LLMs can approximate human judgments in checklist-based appraisal and (2) whether patterns of human-LLM disagreement can be used to identify and improve ambiguous checklist items. Using the Guidelines for Reporting on Latent Trajectory Studies (GRoLTS) checklist, we compare LLM-generated assessments with expert annotations across three research topics and two checklist versions. Agreement is assessed using item-level accuracy, chance-corrected agreement, and preservation of study-level rank ordering. We find that performance varies subs
arXiv:2608.20382v1 Announce Type: new Abstract: We introduce a new architecture design for multimodal large language models (MLLMs), Libra, capable of both multimodal understanding and generation. Libra architecture contains one vision system and one language system, connected by cross-modal bridges. This design decouples self-modal modeling and cross-modal interaction, enabling each modality to learn its unique representations while maintaining effective cross-modal comprehension. The decoupling is mainly achieved in a switch attention module and a switch FFN module, which dynamically routes the computation flow for self-modal modeling and cross-modal interaction scenarios. We evaluate the effectiveness in two important settings: \textbf{Libra-1} for the understanding-only image-to-text setting, and \textbf{Libra-2} for unified image-to-text understanding and text-to-image generation. In addition to the architecture design, we discuss various improvements on tokenization, positional e
arXiv:2608.20376v1 Announce Type: new Abstract: LLM agents can now generate realistic shilling profiles, fluent reviews, and coherent ratings at scale, systematically defeating recommender-system defenses. Text-only detectors that flag semantic drift in review embeddings are blind to graph structure and temporal coordination, while graph-only detectors that exploit neighborhood anomalies cannot reason over review semantics or the cross-modal inconsistencies produced by LLM-generated content. We propose TH-GNN, a heterogeneous temporal graph neural network with a two-layer Heterogeneous Graph Transformer backbone that applies per-type and per-relation attention augmented with learnable sinusoidal temporal encodings on every edge. Cross-modal attention fuses structural user embeddings with frozen RoBERTa representations of reviews and item descriptions, while a GRU operating over log inter-arrival times captures temporal burstiness. Evaluated across five attack families and four benchmar
arXiv:2608.20375v1 Announce Type: new Abstract: Tree-based speculative decoding raises the mean accepted tokens of standard speculative decoding by verifying multiple draft paths, and existing tree builders typically construct these paths through parent-conditioned expansion, where each child token is generated conditioned on its parent path. This construction is incompatible with diffusion language model (DLM) drafters such as DFlash, which produces all future-position distributions in a single forward pass. DDTree bridges this gap by treating high-probability tokens from each future-position distribution as candidate nodes and selecting edges between consecutive positions under a fixed node budget. However, its edge selection relies on token probability alone without modeling parent--child compatibility, so target-compatible tokens can be attached to wrong parents; moreover, its fixed budget ignores that the throughput-optimal tree size varies with the decoding state. We propose GRAF
arXiv:2608.20374v1 Announce Type: new Abstract: How precisely can we tell a language model how to feel? Most work on emotional generation answers with a discrete label - happy, angry, sad - which cannot express a target like "mildly downcast but calm." We instead specify the desired affect as a continuous point (v*, a*) in the Valence-Arousal plane and train the model to hit it. Our method, VA-DPO, is a small modification to Direct Preference Optimization: a frozen VA regressor scores each sampled generation by its Euclidean distance to the target, we keep only candidate pairs whose distance gap clears a margin tau, and we optimize a LoRA adapter with the ordinary DPO loss against a frozen reference. The DPO objective itself is unchanged; what is new is how the preference data is built. On Llama-3.1-8B-Instruct this cuts mean VA distance to the target by 33% over system-prompting and 25% over few-shot prompting, lifting valence/arousal correlation to r_v=0.93 and r_a=0.75. The gains ca
arXiv:2608.20373v1 Announce Type: new Abstract: Objective: To evaluate large language model (LLM) performance on unprocessed electronic medical record (EMR) data for clinical registry abstraction. Methods: We evaluated LLM performance answering registry questions for the American College of Cardiology National Cardiovascular Data Registry (ACC NCDR). In a pilot study at an academic medical center, the model identified candidate data sources for each registry question and experienced abstractors used these results to define question-specific document sets. In a validation study at a second center with a second ACC NCDR registry, the LLM answered questions using the question-specific document sets. Before reviewing any output, two abstractors independently established the ground truth and assigned each question to one of six categories, ordered by the ambiguity and clinical reasoning required to resolve it: Medication/Event Flag, Binary Clinical Presence, Administrative, Quantitative Lab
arXiv:2608.20371v1 Announce Type: new Abstract: A common claim is that zero-shot large language models (LLMs) can replace fine-tuned NLU classifiers for intent detection. We test this claim head-to-head and find that the honest answer is: it depends on the intent space. On full ATIS and CLINC150 we compare a fine-tuned RoBERTa, a TF-IDF+logistic-regression baseline, sentence-embedding kNN, and Claude Haiku zero-shot, reporting bootstrap 95% confidence intervals and paired significance tests. When abundant in-domain labels exist, fine-tuned RoBERTa is as good or better and three orders of magnitude cheaper and faster: on ATIS it beats Claude zero-shot by 11.8 points (95.9 vs. 84.1, p<0.001). On the broad 150-intent CLINC150 schema the two are statistically tied (89.1 vs. 88.5, p=0.24): the LLM matches a fully supervised model with no training data. The LLM's advantages appear in three production-relevant regimes: out-of-scope detection (OOS recall 85.6 vs. 58.1 for RoBERTa); robustness
arXiv:2608.20369v1 Announce Type: new Abstract: Structured reporting converts free-text radiology narratives into queryable data keys, facilitating cohort assembly, longitudinal tracking, and training label generation for medical AI. The prevailing paradigm follows a two-stage pipeline: (1) constructing a reporting template, (2) extracting information to populate it. While the extraction stage has benefited from advances in large language models (LLMs), template construction remains a manual bottleneck relying on labor-intensive expert consensus that is static, difficult to scale, and may fail to capture real-world reporting diversity. We address this limitation with \textbf{\texttt{ASTAR}}, an LLM-based framework for Automated induction of STAndardized radiology Reporting templates from large-scale clinical free-text corpora. Extensive experiments on 4,215 fetal brain MRI reports from multiple centers demonstrate that the \textbf{\texttt{ASTAR}}-induced template surpasses two expert-c
arXiv:2608.20368v1 Announce Type: new Abstract: Knowledge and innovations are shaped by using the quality and credibility of the scientific research. Yet, distinguishing between impactful, high-quality work and flawed studies remains a challenge. This paper introduces a benchmark for classifying research papers into two categories: good (highly cited) and non-good (retracted), using only textual features from titles and abstracts. We evaluate multiple embedding techniques, including SBERT, Word2Vec, FastText, USE, and TF-IDF, combined with classifiers such as Support Vector Machines (SVM), Random Forests, and Neural Networks. Our contributions include: (1) hyperparameter transparency, (2) feature space visualizations using t-SNE, (3) model interpretability analysis with SHAP, and (4) detailed examination of error cases. Experimental results show that a neural network with SBERT embeddings achieves 87.22\% accuracy, while FastText combined with SVM reaches 91.12\%. These findings highli
arXiv:2608.20365v1 Announce Type: new Abstract: Sri Lankan parliamentary debates (Hansards) constitute a trilingual corpus of speeches in Sinhala, Tamil, and English, including code-mixed content, yet remain inaccessible to standard NLP pipelines due to layout-complex PDFs, multilingual scripts, and agglutinative morphology. We present an end-to-end framework that addresses these challenges through LLM-based text extraction followed by a multilingual embedding and density-based clustering pipeline for topic modeling. A hybrid semantic-lexical extension, BiTopic, is further explored to improve interpretability and recover speeches otherwise discarded as noise. Applied to 19,553 speeches spanning 2017-2026, the pipeline recovers 30 macro-topics achieving a cluster purity (BCP) of 0.673, whose temporal trajectories align unsupervised with major national events including the 2019 Easter Sunday attacks and the 2022 economic crisis. Traditional LDA fails on this corpus due to cross-lingual f
arXiv:2608.20364v1 Announce Type: new Abstract: We examine how hadith computational science is being reshaped by transformer models, retrieval-grounded pipelines, and large language models (LLMs). Recent reviews document growth in the literature, but they do not yet provide a critical account of which advances are methodologically robust, which remain benchmark-bound, and which unresolved problems still limit scholarly use. We address this gap through a critical narrative review that combines critique of existing reviews, paper-level appraisal of representative original studies, and synthesis of Islamic scholar and domain-expert perspectives on authenticity, authority, and responsible use. We find uneven progress. Data resources have expanded, segmentation tasks have matured, narrator and source-verification problems are better formalized, and LLM-assisted workflows now support corpus-scale enrichment, multilingual access, and grounded evaluation. At the same time, progress remains con
arXiv:2608.20362v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is a standard recipe for training large language models on mathematical reasoning, where an answer verifier serves as a language-neutral reward function. We show that this assumption fails in multilingual settings: an exact-match verifier turns format and script variation into language-dependent false-negative reward noise. We introduce a reusable protocol for auditing multilingual RLVR rewards: a verifier-robustness suite, a rollout-diagnosis procedure, and language-conditioned reward-error metrics for Japanese, English, and Chinese answers. On MGSM rollouts with k=8, the exact-match proxy rejects trusted-correct answers at sharply different rates by language across Qwen3-4B, Qwen3-8B, and Llama-3.1-8B-Instruct; for Qwen3-8B, the false-negative rate reaches 0.642 on JP against 0.122 on EN and 0.073 on CN. A plain-numeric probe localizes the mechanism to the final-answer interface: an
arXiv:2608.20361v1 Announce Type: new Abstract: Automated research-idea generation systems built on large language models (LLMs) share a structural weakness: they reduce ideation to free-text recombination, random paper pairing, or embedding-similarity retrieval. The three approaches fail in the same way: each treats a paper as a flat object, a string or a vector, and so quotients away the typed problem-method-metric-claim arrows a researcher actually uses when reasoning about a cross-domain analogy. We recover the missing structure with the minimal piece of category theory that a typed graph alone does not provide: composition, together with identity arrows, which makes it possible to ask whether a proposed analogy preserves relation chains. Concretely, each paper $p$ is modelled as a small category $C_p$ whose objects are extracted typed research entities and whose morphisms are the relations the paper asserts; a cross-paper bridge from $p$ to $q$ is then a partial functor candidate
arXiv:2608.20360v1 Announce Type: new Abstract: We study whether tiny decoder-only language models benefit from feed-forward layers that directly multiply learned feature projections. TriPLU, a Trilinear Product Linear Unit, replaces the usual gated FFN branch with a product-only degree-3 branch that multiplies three projected streams coordinatewise. In a character-level TinyStories 1M-byte prefix study, TriPLU reaches a mean best validation loss of 1.0637, compared with 1.1017 for closely matched SwiGLU, 1.0780 for a degree-4 product control, and 1.1026 for a degree-2 control. In train-only Byte-BPE experiments, TriPLU also lowers validation and heldout bits per byte on TinyStories and WikiText-2 raw under low-learning-rate settings, with PMI-slice evidence suggesting gains on seen middle- and high-PMI adjacent-token pairs. Constant-learning-rate diagnostics show that product-branch normalization can reduce the high-learning-rate best-checkpoint gap, although final BPB still degrades
arXiv:2608.20359v1 Announce Type: new Abstract: Large language models (LLMs) are deployed for increasingly complex tasks involving planning and multi-step decision making, but high-quality performance on these tasks often requires generating long reasoning traces. This is a poor fit for latency-sensitive and interactive applications like voice assistants or coding agents, where generation latency can strongly affect user experience. Existing acceleration methods typically focus on token-level generation, without utilizing the structure of reasoning workflows. We introduce SSR: Self-Speculation for Reasoning Models, a training-free self-speculative decoding method that leverages the chain-of-thought (CoT) as a source of speculation. SSR uses the partial-CoT answer distribution as the drafter and the full-CoT distribution as the verifier, deriving both from the same model at different reasoning budgets. This builds on the observation that later partial-CoT responses often exhibit greater
arXiv:2608.20355v1 Announce Type: new Abstract: Large Language Model (LLM) agents have demonstrated considerable potential for social simulation, yet struggle to accurately model individual value systems. Most existing methods mechanically stitch survey responses into prompts, which suffer from semantic fragmentation, failing to capture the internal coherence of human value systems. The value systems of LLMs are typically assessed using static multiple-choice questions, which fail to evaluate the value orientation in real-world dialogue interactions. To address these issues, we propose ExpertIVS, a framework employing 14 Sociological Expert Agents to interpret World Values Survey (WVS) responses through structured professional perspectives, rather than direct responses concatenation. These expert agents perform deep semantic reconstruction to generate robust and internally consistent individual profiles. To evaluate the consistency between LLMs and individual value systems during dynam
arXiv:2608.20353v1 Announce Type: new Abstract: Computational mental health (CMH) classifiers often degrade under distribution shift because human annotators and distant-supervision pipelines reward different linguistic signals. We introduce TSS (Triple-Stream Stress probe), a multi-channel diagnostic framework that decomposes text into (A) lexical character n-grams, (B) a small, mostly content-free morpho-syntactic channel, and (C) a 154-feature psycholinguistic style channel. Across four English datasets (N=12,906), TSS reveals a lexical interference effect: adding lexical features to the style channel reduces Macro-F1 on human-labeled data (mean drop 0.072, p<10^-4) but not on auto-labeled data. We propose Degree of Divergence (DoD), a difference-in-differences statistic adapted from econometrics for label-source auditing, with instance-level bootstrap inference; the headline estimate is DoD(BC-A) = 0.0374, 95% CI [0.0097, 0.0651], p=0.0032. A platform-stratified Twitter-only DoD (w
arXiv:2608.20350v1 Announce Type: new Abstract: Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. These systems often fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high latency. We propose OneModel, an applicable paradigm shift from external workflows to internalized knowledge representation. Unlike modular systems that slice fluid user intents into static steps, OneModel consolidates complex business logic and SOPs directly into the model parameters. Through Continual Pre-training (CPT) and logic-compilation SFT, we transform fragmented business rules into intuitive model reasoning within a unified attention space. Deployed in our global financial service system, OneModel effectively breaks the trade-off between latency, accuracy, and complexity. Online A/B testing demonstrates an end-to-end latency reduction of more than 50 percent, from 18.7 seconds to 8.0
arXiv:2608.20349v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit extreme sensitivity to surface-level prompt variations, in which minor lexical changes can trigger disproportionate performance fluctuations. Moving beyond black-box optimization and coarse-grained templates, we present the first large-scale, n-gram token-level mechanistic analysis of prompt stability, leveraging a dataset of 132,000 prompt variants. Our investigation reveals a fundamental Scaling Law of Prompt Performance Stability: higher average task performance is strongly associated with lower variance and greater robustness across prompt perturbation. We identify two core linguistic drivers underlying this robustness: (1) Domain-Specific Terminology, which tightly anchors semantic boundaries, and (2) Explicit Action Directives, which formalize reasoning trajectories. Together, these elements constrain the model's interpretative space, effectively ``locking in'' more deterministic generation behav
arXiv:2608.20348v1 Announce Type: new Abstract: Electronic health records now routinely exceed 100,000 tokens per patient. Yet large language models exhibit the lost-in-the-middle (LitM) effect: information near the center of a long context is retrieved less reliably than information near the edges. In clinical use this is not benign: the single most consequential fact in a note can sit at its center. We term this the clinical lost-in-the-middle (CLitM) problem, give its first systematic characterization using MedAlign, and compare context-selection strategies as remedies. Across 2,196 instruction-response pairs and six language models, we observe a 21.9 percentage-point gap between peak accuracy (59.5%, 95% CI [46.3, 71.0], 20-30% decile) and trough accuracy (37.6% [23.2, 52.5] at 70-80%); 67.8% of reference answers fall between the 10th and 90th percentiles of the EHR timeline, inside the CLitM trough. We introduce Query-Conditioned Clinical Suppression (QCCS), a lightweight query-co
arXiv:2608.20346v1 Announce Type: new Abstract: Speech systems used in customer-facing applications often require domain-specific language coverage. We present a synthetic Bengali speech dataset for telecom customer-care scenarios. The dataset contains 10,000 audio-text pairs, approximately 26.82 hours of 24 kHz speech, and predefined train, validation, and test splits of 9,000, 500, and 500 examples. It is publicly released on Hugging Face under the CC-BY-4.0 license. The speech was generated with OmniVoice in voice-cloning mode using a real female reference recording and transcript, with bfloat16 precision, 16 diffusion sampling steps, and a speaking-rate control value of 1.0. Along with the original Bengali text, the dataset provides a normalized transcript field designed for ASR/STT training and evaluation. We report an automatic intelligibility check over all 10,000 samples using a domain-adapted Whisper ASR model fine-tuned from bengaliAI/tugstugi_bengaliai-regional-asr_whisper-m
arXiv:2605.26620v2 Announce Type: replace-cross Abstract: Natural language conveys information at varying levels of granularity, from fine-grained references to broad descriptions. While granularity is fundamental to human communication, existing measures mostly capture surface detail or sentence specificity. We introduce Granuscore, a reference-free measure of granularity that leverages structural properties of a hierarchical embedding space. Granuscore reliably recovers hierarchical orderings on the Granola-EQ dataset and captures expected differences in granularity across discourse contexts. Across domains, we further show that Granuscore explains non-linear variation in sentence specificity beyond sentence length. Finally, we apply Granuscore to four question-answering benchmarks and analyze how granularity differs for questions, gold answers, and model outputs across response outcomes. The analysis reveals consistent differences in model behavior and provides a principled lens for
arXiv:2604.20166v3 Announce Type: replace-cross Abstract: Language-based AI is increasingly deployed for mental health support, yet trust is evaluated in interdisciplinary but operationally misaligned ways: NLP and AI work measures robustness, safety, privacy, and explanations, while psychotherapy, HCI, and regulatory work emphasize therapeutic fidelity, lived experience, empathy, and reliance. Empathetic chatbots can elicit strong user trust without commensurate safety, while safer systems are under-trusted when their boundaries are opaque, a calibration gap no single community owns. Through a structured scoping synthesis of 61 papers, we survey this landscape into a three-layer framework separating (L1) human-oriented trust, (L2) interaction-oriented trustworthiness, and (L3) AI-oriented trustworthiness, and map five stakeholder perspectives onto these layers. We outline a research agenda for building socio-technically aligned trustworthy AI for mental health support, highlighting th
arXiv:2512.00418v3 Announce Type: replace Abstract: Significant Others (SOs) stabilize identity, regulate emotion, and support narrative meaning-making, yet many people today lack access to such relational anchors. Recent advances in large language models and memory-augmented AI raise the question of whether artificial systems could support some of these functions. Existing empathic AIs, however, remain reactive and short-term, lacking autobiographical memory, identity modeling, predictive emotional regulation, and narrative coherence. This manuscript introduces Significant Other Artificial Intelligence (SO-AI) as a new domain of relational AI. It synthesizes psychological and sociological theory to define SO functions and derives requirements for SO-AI, including identity awareness, long-term memory, proactive support, narrative co-construction, and ethical boundary enforcement. A conceptual architecture is proposed, comprising an anthropomorphic interface, a relational cognition laye
arXiv:2506.13583v2 Announce Type: replace Abstract: Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers, which can result in suboptimal feedback in collaborative teaching settings. Yet, how humans perceive and interpret RL agent's learning behavior is largely unknown. In a bottom-up approach with two experiments, this work provides a data-driven understanding of the factors of human observers' understanding of the agent's learning process. A novel, observation-based paradigm to directly assess human inferences about agent learning was developed. In an exploratory interview study (\textit{N}=9), we identify four core themes in human interpretations: Agent Goals, Knowledge, Decision Making, and Learning Mechanisms. A second confirmatory study (\textit{N}=34) applied an expanded version of the paradigm across two tasks (navigation/manipulation) and two RL algorithms (tabular/function approximation). Analyses of 816
arXiv:2608.21083v1 Announce Type: cross Abstract: Successful Human-Robot Teaching assumes alignment between robot processing needs and human teaching intent. To better understand this alignment, this work seeks to uncover the underlying logic that humans intuitively apply when teaching. Through an exploratory, bottom-up study with N=34, participants observing two distinct robot Reinforcement Learning (RL) scenarios, we analyze 204 intuitive teaching responses across early, middle, and late learning phases. Results reveal that teaching decisions consist of a nuanced, interconnected network of Triggers (situational catalysts), Objectives (subjective teaching targets), Signals (communicative acts), and Strategies (high-level governance) in which teachers spontaneously adopt diverse roles, acting as coaches, engineers, or designers and prioritize different objectives. Based on these results, we introduce the TOSS Framework, which conceptualizes Human-Robot teaching as a procedural loop bet
arXiv:2608.21074v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in research workflows and software development pipelines, yet their output remains sensitive to input prompt variations. This paper presents $\unicode{x00AB}$PromptResponse$\unicode{x00BB}$, a controlled study examining how formatting and LLM-based tuning of coding task prompts affect the resulting code's performance, efficiency, and stability. Using five semantically identical yet syntactically distinct variants of the HumanEval dataset$\unicode{x2014}$baseline, JSON, Markdown, YAML, and an LLM-tuned version$\unicode{x2014}$we had GPT-4o solve its coding problems over 8200$\unicode{x00A0}$executions. Our results show that consistent formatting$\unicode{x2014}$especially JSON$\unicode{x2014}$improves generation efficiency and syntactic stability, with minor gains in task performance. Conversely, the LLM-tuned prompts resulted in significantly degraded task performance without significan
arXiv:2608.20983v1 Announce Type: cross Abstract: False information spreads rapidly on social media during disasters and can undermine emergency response efforts, public trust, and crisis communication. Existing research primarily focuses on determining whether social media posts contain false information, but provides limited insight into the specific false claims embedded within posts and the severity of individual false claims. To address the limitations, we propose a two-stage framework to assess the severity of false claims during disasters. In the first stage, we develop a false claim extraction agent that identifies false claims from multimodal social media posts containing text, images, videos, and links. A subsequent verification step validates extracted claims with supporting evidence. In the second stage, we define false claim severity as the combination of two complementary dimensions: believability, which determines the likelihood that a claim will be believed, and harmful
arXiv:2608.20896v1 Announce Type: cross Abstract: Programming error messages are critical for software development, yet they remain difficult for novice programmers to interpret. While Large Language Models (LLMs) can rewrite these errors into clearer explanations, it remains unclear whether increased readability improves objective debugging performance or how explanation styles should align with programmer skill. We present a multi-stage crowdsourced study N=103 evaluating skill-targeted, LLM-generated Python error messages. Using a custom proficiency assessment, we categorized participants by skill level and tested standard interpreter messages against two LLM-generated styles: pragmatic (action-oriented) and contingent (scaffolded explanations). We measured both objective debugging metrics (fix rate, attempts, time-to-fix) and subjective perceptions (readability, cognitive load, tone). Our results show that while LLM-rewritten messages significantly improved subjective evaluations,
arXiv:2608.20807v1 Announce Type: cross Abstract: Environmental exposures such as air pollution and greenness have been associated with affective and cognitive outcomes, but EEG and environmental datasets are rarely jointly georeferenced. We investigate whether literature-informed environmental priors can serve as an auxiliary geospatial modality for EEG-based affective-state classification when individual-level exposure data are unavailable. We combine 30-channel EEG from the EAV benchmark (42 participants, aged 20-30 years) with environmental representations derived from OpenAQ, Sentinel-2, Sentinel-5P, and OpenStreetMap data for Astana. A dual-tower architecture combines EEG-Conformer representations with a graph-based environmental encoder. Because the datasets are not co-registered, environmental context is treated as a literature-informed prior rather than measured exposure. Subject-level repeated splits, permutation and label-shuffling controls, dose-response reversal, and domai