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:2608.22917v1 Announce Type: new Abstract: We present TSWAP, a deployed eight-language conversational wellness advisor grounded, via retrieval-augmented generation, in a verified knowledge base of Thai traditional medicine and certified wellness providers. An unmodified open-weight LLM (Qwen3.6-35B-A3B on vLLM) is grounded on a ~30.6K-chunk Thai index by a hybrid dense-sparse retriever with cross-encoder reranking; a first-turn query classifier forces tool-based retrieval for entity lookups; a rule-based safety layer enforces medical scope and Thai emergency routing; and all eight languages are served zero-shot with translate-then-retrieve. We release the first Thai traditional-medicine/wellness retrieval benchmark (50 questions with gold document IDs; Recall@5 = 0.88), production QA logs (91.1% test-retest pass over 259 cases), and a 71-question frontier no-retrieval probe showing what each grounding pillar contributes: without the safety prompt the backend model family produced
arXiv:2608.22916v1 Announce Type: new Abstract: Vision-language models are known to encode spatial information in their hidden states, yet often fail to use it when answering. However, it remains unclear when and where this encoded information reaches the answer. We address this with direction patching, a class-conditioned causal intervention applied across layers, token positions, and prompt formats. Using spatial-ID directions constructed following prior encoding evidence, we find that causal influence on answer logits emerges only at mid-to-deep depths. Text chain-of-thought suppresses immediate object-word argmax-level transport in most models, while visually grounded prompts keep it open. Positive target-logit gain can remain below the argmax threshold, and transport can re-emerge at the final prefix token or at the answer step in deeper layers. Across the ten VLMs we study, these local effects form descriptive transport patterns. Complementary experiments characterize how these p
arXiv:2608.22909v1 Announce Type: new Abstract: Dowker homology is a topological tool that may be used to analyze the relative position of two point clouds living in a common space. We investigate whether Dowker homology captures sentence similarity information by treating the embeddings of the tokens that constitute a sentence pair as a pair of point clouds in the latent space of a transformer model, using both models that have and have not been fine-tuned for sentence similarity. We find that Dowker homology captures sentence similarity information, as measured by regressing Dowker homology features onto ground-truth similarity scores, and that it can be used for visual inspection of similarity data and models. In an attempt to make Dowker homology readily applicable, we derive from it single-number summaries that we expect to capture sentence similarity directly. These turn out to work reasonably well, but without outperforming standard sentence similarity measures based on establis
arXiv:2608.22908v1 Announce Type: new Abstract: Spoken Language Models (SLMs) generate textual responses directly from speech, offering an alternative to cascaded systems. Despite recent advances, existing SLMs still exhibit weaker instruction-following behavior and limited generalization across diverse tasks compared to text-based language models. Our analysis shows that speech and text representations in current SLMs remain weakly aligned despite strong downstream performance, indicating that structural differences between continuous, temporally varying speech and discrete text remain insufficiently addressed. To address this, we propose a simple framework that decouples length mismatch from semantic alignment and encourages closer correspondence between speech and text representations. Experiments across multiple benchmarks demonstrate competitive performance against strong baselines, underscoring the importance of explicitly addressing structural differences between speech and text
arXiv:2608.22898v1 Announce Type: new Abstract: Diffusion language models (DLMs) alleviate the inherent latency bottleneck of autoregressive (AR) large language models (LLMs), but their degraded generation quality limits practical applicability. Although knowledge distillation (KD) can be a promising direction for improving performance, we empirically find that naively applying conventional KD yields only marginal gains, or even degrades generation quality. Based on these observations, we propose a novel self-distillation framework for DLMs, namely SelFusion. To enable effective KD without an external teacher model, SelFusion performs two forward passes with different masking levels, defining the hard mode with a larger masking probability and the easy mode with a smaller masking probability. However, the easy mode is not always more accurate than the hard mode and can be overconfident on incorrect tokens. Thus, we introduce bidirectional KD between the two modes, which can dynamically
arXiv:2608.22894v1 Announce Type: new Abstract: Arabic harmful-language detection has received considerable attention, yet Arabic text detoxification remains underexplored. We introduce AraDetox, a multi-dialect Arabic detoxification dataset comprising 10,500 harmful social-media posts and 84,000 detoxified rewrites generated using GPT-5 and Gemini 2.5 Flash across Modern Standard Arabic, Gulf, Levantine, and Egyptian Arabic. The generated outputs were assessed through human evaluation and automatic analyses of lexical change, semantic preservation, sentiment, and dialectal style. Results show that detoxification is primarily a meaning-preserving rewriting task: substantial lexical and structural reformulation is accompanied by consistently high semantic similarity. Human evaluation confirms successful harmful-language removal while largely preserving the original meaning. Dialectal analyses further indicate that the generated variants exhibit measurable stylistic alignment with refere
arXiv:2608.22872v1 Announce Type: new Abstract: Speech-based applications pass spoken queries through automatic speech recognition (ASR) before any retrieval module, so ASR errors enter the pipeline as a fixed upstream constraint. We empirically test whether two extensions to standard retrieval-augmented generation (RAG), entity-graph linking and iterative reformulation, absorb or amplify these errors. Using four English accents synthesized through neural TTS, we evaluate four RAG configurations on three multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA and MuSiQue) against a clean-text oracle. Although the structurally richer configurations generally retain higher absolute F1 under ASR input, both extensions amplify the error: the F1 gap from clean text to the highest-WER accent is 36-67% larger under their combination than under naive dense retrieval, on all three benchmarks. The dominant failure mode is corruption of one or more query entities, accounting for 87-96% of degradation
arXiv:2608.22857v1 Announce Type: new Abstract: Vision-language models (VLMs) frequently fail at visual change reasoning, even when their vision encoders contain sufficient information. We observe that correct VLM outputs tend to contain explicit verbal evidence (object names, colors, spatial locations) that supports the claimed change, while incorrect outputs often lack such evidence. We propose SAVER (Selective Auditing of Verbal Evidence for Error Recovery), a lightweight, rule-based method that parses VLM responses for this evidence and triggers structured reprompting only when evidence is missing or inconsistent. Across three change detection benchmarks and four VLMs, SAVER significantly improves accuracy on tasks where errors stem from the model failing to articulate what it saw (expression failures), with gains up to +25.8% on CLEVR-Change. The evidence patterns can also be generated by an LLM in a single call, matching the hand-tuned gate on CLEVR-Change. Ablation experiments c
arXiv:2608.22817v1 Announce Type: new Abstract: Industrial technical reports contain high-value knowledge for maintenance, troubleshooting, and product engineering, but their heterogeneous structure (dense prose, specifications, tables) makes them difficult to index and reason over with standard retrieval and QA pipelines, and no public instruction-tuning or benchmark datasets are built from such documents. We address this gap with Industrial-Instruction, contributing (i) two open QA datasets built from real industrial technical reports and (ii) the end-to-end pipeline that produces them. Using 906 public Panasonic documents (7,525 pages), we apply layout-aware extraction, build a semantic retrieval index, and synthesize multiple-choice QA grounded in retrieved evidence under five query-document relationships (irrelevant retrieval, single-/multi-document support, single-/multi-document answer). After filtering an initial 23.9k generated samples, each dataset provides approximately 13.6
arXiv:2608.22806v1 Announce Type: new Abstract: Iterative preference optimization is essential for aligning Large Language Models on mathematical reasoning tasks, yet its efficiency is often throttled by signal scarcity: as the model improves, static problem sets become increasingly mismatched to the model's evolving competence, producing rollouts that are either too easy or too hard and therefore non-informative, which leads to a scarcity of valid preference pairs. We propose DIAG, a Diagnostic Iterative Alignment and Generation framework that adaptively reshapes the practice distribution to increase informative supervision and focus training near the student's current competence boundary. DIAG consists of two phases: (1) diagnosing valid preference-pair yield to calibrate the exploration-exploitation trade-off and allocate topic quotas via an Empirical Bayes shrinkage estimator, thereby prioritizing high-yield concepts; and (2) generating targeted practice, where a teacher synthesize
arXiv:2608.22802v1 Announce Type: new Abstract: Medical large language models are often judged by how many clinical questions they answer correctly. That view is useful, but it misses a practical risk. A model may know the right answer and still change its response when the same case is written in a different patient voice. This paper evaluates that risk as SDoH aware narrative anchoring bias. We use NarrativeShield SDoH MedQA, a counterfactual medical question answering dataset in which each case appears in persona based narratives while the answer key remains fixed. The dataset is reshaped from wide format into case grouped persona rows. We evaluate three open source instruction tuned LLMs from the Qwen2.5 family: 1.5B, 3B, and 7B. The final experiment uses 300 clinical cases and produces 8,100 model responses across three prompting conditions. We report persona level accuracy, counterfactual consistency, correct consistency, and narrative sensitivity error. Qwen2.5 7B achieves the b
arXiv:2608.22793v1 Announce Type: new Abstract: Reliable deployment of LLM agents in user-facing products depends not on raw task-solving ability but on consistency and limit-awareness: behaving the same way across repeated trials, and recognizing when a request cannot, or cannot yet, be safely fulfilled. CAR-bench exposes this reliability gap in the domain of in-car assistants: an LLM-simulated user issues incomplete or ambiguous requests, requiring the agent to resolve uncertainty through multi-turn dialogue and tool use while strictly adhering to domain policies. Even frontier models show a substantial gap between what they can solve at least once (Pass@3) and what they solve consistently across trials (Pass^k). We bridge this gap with TRACE (TRAjectory-Contrastive Evolution), which iteratively improves a skill-based agent's behavioral knowledge without modifying model weights. This knowledge is organized as a Skill Bank of modular, retrievable skills, each encoding a self-contained
arXiv:2608.22772v1 Announce Type: new Abstract: Text-to-SQL aims to translate natural language questions into executable SQL queries over relational databases, requiring multi-stage structured reasoning over database schemas and query constraints. However, existing methods treat this task as single-step generation, where models optimize entire SQL sequences without targeted feedback at key decision points and lack support for interacting with and controlling the intermediate generation process. To address this issue, we propose SPOC-SQL, which decomposes Text-to-SQL into four sequential subtasks following standard SQL execution logic and designs stage-specific optimization strategies for the model to learn key decisions. Specifically, we propose the implementation of fine-grained preference optimisation at key decision points across SQL stages, with the objective of enhancing structured decision-making during query construction. Furthermore, a structured decomposition strategy is desig
arXiv:2608.22770v1 Announce Type: new Abstract: Financial institutions need an independent way to detect missing, stale, and misclassified corporate-event records in vendor databases. We introduce Search-to-Record, a database-assurance task in which search-enabled large language models reconstruct institution-defined event records from public sources for a known security universe and historical cutoff, and DelistBench, a 1,200-record benchmark for security-level delisting announcements. We evaluate five models in paired closed-book and web-enabled conditions. Web access raises announcement-date accuracy within seven days by 34.0 to 48.0 percentage points and event-status accuracy by approximately 2.8 to 21.7 points; the best system achieves 81.5% overall joint accuracy within seven days. Economy web systems achieve 75.9-78.3% overall joint accuracy within seven days at 4.5-6.6% of the API cost of the most expensive web system. Risk-based triage identifies low-error subsets, although th
arXiv:2608.22761v1 Announce Type: new Abstract: Large Language Models generate text autoregressively, but open-ended generation is prone to verbatim looping, in which models repeat spans already present in context. Standard defenses such as repetition, presence, and frequency penalties and n-gram blocking act on token recurrence rather than the sequential structure of a loop, and often suppress looping only at strengths that also degrade formatting or fluency. We propose Don't Repeat Yourself (DRY), a sampling-time logit adjustment that penalizes a candidate token only when generating it would extend the current suffix into an exact continuation of a span seen earlier in the context. Sequence breakers protect chat templates and formatting tokens. Across models from 1.5B to 120B parameters, nine prompt families, and a 600-pair human study, DRY reduces suffix-extension rate by 47% while improving lexical diversity. An intervention-matched placebo produces no comparable reduction, identif
arXiv:2608.22758v1 Announce Type: new Abstract: Standard decoding rules for autoregressive language models promote diversity by rescaling the full next-token distribution or truncating its low-probability tail. These strategies overlook a common regime of open-ended generation in which several continuations are plausible but too much probability mass remains concentrated on the most generic choice. We introduce XTC (Exclude Top Choices), a lightweight head-aware decoding operator that targets this regime directly. XTC identifies tokens whose probabilities exceed an absolute plausibility threshold $\tau$: when at least two qualify, it removes the dominant eligible choices with probability $\rho$ and retains only the weakest plausible alternative before renormalization. Across 60 experiments on Gemma 3 27B Q4, Gemma 3 12B Q6, and DeepSeek R1 14B Q6, with scaling validation on Llama 3.3 70B Q4, XTC improves the diversity-repetition Pareto frontier. On creative generation, Distinct-2 incre
arXiv:2608.22753v1 Announce Type: new Abstract: Large language models (LLMs) excel at text understanding and generation, yet still struggle to reliably understand and apply externally provided procedural rules at scale. To evaluate this capability, we introduce RuleWorld, a large-scale benchmark that reformulates rules as globally reusable abstract units rather than instance-specific facts. In RuleWorld, several scenarios, including single-rule, parallel multi-rule, and multi-hop reasoning, are settled for comprehensive evaluation. We further propose DynaRule, an end-to-end framework that injects the given rules into the KV cache and turns retrieval into an internal, learnable, step-wise process. Specifically, DynaRule employs Stacked Step-Level Attention Training with a special token to enable dynamic rule re-attention and updating during inference. In this way, the model can re-attend to the most relevant rules at each step, dynamically replacing outdated ones to support more stable
arXiv:2608.22745v1 Announce Type: new Abstract: Emotion Recognition in Conversation (ERC) requires models to identify subtle emotional cues that are often distributed across distant dialogue turns. Existing methods typically incorporate dialogue history through a fixed context window. However, short windows discard potentially useful long-range evidence, while enlarging the window repeatedly re-encodes overlapping utterances, increases computational and memory costs, and may introduce irrelevant context. Moreover, commonly used parameter-efficient adaptation methods, such as LoRA, mainly introduce fixed low-rank transformations in the feature space and do not explicitly maintain a dialogue-level state or condition their transformations on the evolving conversational context. To address these limitations, we propose a lightweight adapter, DiaRelay, to enable LLMs to explicitly maintain a dialogue-level memory for accurate ERC. Based on LoRA, DiaRelay introduces two extra tightly collabo
arXiv:2608.22713v1 Announce Type: new Abstract: Clinical diagnosis requires progressive integration of patient history, physical examination, laboratory findings, medical images, and diagnostic-informative tests. However, most multimodal medical benchmarks evaluate fixed inputs or endpoint answers, while fully interactive diagnostic agents conflate evidence selection with evidence interpretation. We present a source-grounded framework to construct progressive multimodal diagnostic dialogues from case reports and an evaluation strategy for assessing MLLMs on final diagnosis, diagnostic reasoning, and image-finding interpretation. Evaluation on 24 internal medicine case reports showed that our framework can accurately convert case reports into reference dialogues, achieving a diagnosis F1 of 0.99 and a reasoning-quality score of 4.79 out of 5. Evaluation on two frontier MLLMs (o4-mini and Claude Haiku 4.5) achieved reasoning-quality scores of 2.75 and 2.50, respectively, with substantial
arXiv:2608.22704v1 Announce Type: new Abstract: Long-form audio inputs make the KV cache the dominant memory cost of speech LLMs. Prefill-only KV compression methods permanently discard audio KV positions once evicted, with no pathway to recover them during decoding. We show this is fragile on long-form audio: prefill attention concentrates near the audio start (an attention-sink effect), while decode-time attention distributes broadly, and the two rankings overlap weakly. We propose WnW (Waxing-and-Waning KV cache), which classifies KV-heads into anchor, tidal, and fixed roles via offline calibration. Anchor heads remain on GPU and serve as a decode-time importance observer; tidal heads keep a CPU-resident complement that is recalled chunk-by-chunk based on aggregated anchor-head scores; fixed heads keep only an on-GPU subset, with the rest permanently discarded. On LibriSpeech-Long with two 3B backbones (Voxtral-mini-3b and Qwen2.5-Omni-3B), WnW preserves near-Full-Cache accuracy whi
arXiv:2608.22695v1 Announce Type: new Abstract: Agent ecosystems now include thousands of MATS components (Models, Agents, Tools, and Skills), yet their discovery still relies on in-context routing. These systems read a registry (names, hints, or descriptions, as context budget permits), pick a candidate, invoke it, and retry on failure. This pattern degrades with scale, and registries are growing fast. We recast capability discovery as search over a registry by defining an offline enrichment step that turns sparse metadata into searchable profiles, and an online retrieve-then-rank pipeline that returns a ranked shortlist without invoking any candidates online. We show that from N=10 to 7,278 capabilities, in-context routing's top-1 accuracy (Match@1) collapses (0.85 to 0.12), while retrieve-then-rank degrades more gently (0.81 to 0.39) because its reranker still ranks the right capability first 0.70-0.87 of the time once retrieval finds it. In the Nova Micro sweep, the crossover is ar
arXiv:2608.22651v1 Announce Type: new Abstract: Modern text-to-SQL systems have become increasingly elaborate, relying on schema-linking modules, retrieval-augmented prompting, candidate generation, and multi-stage refinement pipelines. While effective, these additions introduce substantial latency and engineering overhead. To this end, we present \textbf{ReAct-SQL}, a simple yet effective zero-shot ReAct-style framework built solely on iterative reasoning and a constrained action space defined by a typed Domain-Specific Language (DSL) of 15 relational operations, rather than free-form SQL generation. The model incrementally issues DSL calls, observes compiled-SQL execution feedback, and revises its reasoning through interaction. On corrected BIRD mini-dev and EHR-SQL, ReAct-SQL achieves \textbf{84.5\%} and \textbf{73.9\%} accuracy, respectively, matching substantially more elaborate baselines while running up to $8\times$ faster. Incremental ablations further show that iteration prima
arXiv:2608.22634v1 Announce Type: new Abstract: Current work on improving reliability in large language model (LLM)- generated answers has primarily leveraged Retrieval-Augmented Generation (RAG), knowledge-graph augmentation, and reinforcement learning. While these methods are adept at enhancing and measuring reliability through semantic similarity and faithfulness, they often struggle to distinguish semantic similarity from geographic validity. This is especially critical in natural hazard management domains where geographic granularity (i.e., town vs. city vs. state) is significant for decision-making, as responses valid in one municipality may not transfer to another. In such domains, a confidently wrong answer carries greater risk than abstaining. We present GeoRisk-RAG, a novel hierarchy-aware framework that addresses this geographic-validity gap through selective answering. This framework explicitly estimates geographic applicability using a Directed Acyclic Graph (DAG)-based di
arXiv:2608.22622v1 Announce Type: new Abstract: Clinical decision-making relies on identifying relevant patient information to guide diagnosis and treatment, a challenge that is especially difficult in the data-dense and rapidly changing intensive care unit (ICU). Large language models (LLMs) could support this task. However, existing applications and datasets mostly emphasize surface-level retrieval or factual recall rather than the inductive and deductive reasoning clinicians practice to select and reason over decision-relevant evidence. We hypothesized that training LLMs on expert ICU reasoning could yield clinical reasoning skills that generalize beyond critical care. Here we introduce ICU-REACT, a reasoning dataset developed with 19 clinicians through a clinician-in-the-loop framework to teach LLMs to perform information retrieval and context-aware clinical reasoning in the ICU. Using ICU-REACT, we fine-tuned Clin-REACT models spanning 8B-70B parameters and three model families. A
arXiv:2608.22566v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems are designed to improve reasoning by decomposing tasks across multiple agents with specialized functions, but the presence of multiple agents does not inherently guarantee coherent reasoning or outputs that align with task objectives. This paper introduces a quantitative ethnographic (QE) approach for diagnosing and redesigning multi-agent LLM systems based on the discourse produced through agent interactions. We test this approach using automated essay scoring as an example context, applying Epistemic Network Analysis (ENA) to model a five-agent multi-agent debate system and examine differences between debates that produced correct versus incorrect scoring decisions. Results show that, in the initial system, correct scoring decisions were characterized by rubric-grounded justification, agreement, and elaboration. Incorrect scoring decisions, in contrast, were characterized by extended propos
arXiv:2608.22506v1 Announce Type: new Abstract: Claim-level Uncertainty Quantification (UQ) aims to mitigate the lack of reliability of Large Language Models (LLMs) by evaluating the factuality of each claim in their outputs. We introduce Kernel Token Contradiction (KTC), a lightweight approach to compute claim-level UQ under realistic white-box conditions. KTC represents the candidate tokens involved in LLM generation as a positive semi-definite kernel that integrates both the LLM's conditional distribution and a token contradiction score. We then use the Von Neumann entropy to quantify the uncertainty of this kernel. To estimate token contradiction, we develop a new approach based on frequency statistics from the Wikipedia corpus. Although CPU-only, our approach achieves over an 8.2x speedup compared to state-of-the-art GPU-accelerated methods based on cross-encoders, and over a 65x speedup compared to CPU-only methods with comparable performance. Our evaluation spans two benchmarks
arXiv:2608.22490v1 Announce Type: new Abstract: Safety alignment helps models adhere to human values, but it often reduces response utility. We ask a critical but understudied question: Does safety alignment impose the cost equally across language groups? To answer this, we introduce a rigorous protocol to measure the utility loss imposed solely by safety alignment, which we term Safety Cost. Through direct pairwise comparisons between safety-aligned models and their unaligned counterparts, we find a systematic inequity: non-English users consistently bear a higher Safety Cost than English users. We further identify three underlying patterns. First, multiple languages lie in a double-penalty zone, experiencing both weaker safety protection and larger utility loss. Second, certain languages exhibit apparent utility gains that are in fact a consequence of safety filters failing to engage. Third, even high-resource languages pay a larger Safety Cost than English to reach the same level of
arXiv:2608.22483v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly support decision-making in high-stakes domains, but they often hallucinate and express confidence that is misaligned with factual correctness. Response-level confidence is a coarse signal: a single generation can mix correct and incorrect statements, so a single number is not actionable for users that must accept, reject, or verify individual pieces of information. We study claim-level confidence calibration as a decision-relevant uncertainty signal: each response is decomposed into atomic, verifiable claims, and each claim is assigned a calibrated confidence using inference-time signals from consistency across samples and self-verification. Our framework operates in closed-box settings (no logits, no fine-tuning) and applies post-hoc calibration directly at the claim level, enabling selective intervention such as evidence retrieval or human review for low-confidence claims. Across TriviaQA and Tr
arXiv:2608.22479v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enables LLMs to access external knowledge for answering knowledge-intensive questions. For complex multi-hop questions, multi-turn retrieval-augmented reasoning extends RAG into an iterative process that repeatedly searches for and integrates evidence across documents. However, existing reinforcement-learning (RL) approaches for agentic RAG are typically optimized with final-answer rewards, which provide sparse supervision and overlook whether the model actually retrieves the required evidence chain. We present \textsc{GTA-RAG}, a graph-trajectory-augmented RL framework for multi-turn retrieval-augmented reasoning. From an entity--document graph, we sample connected document paths, synthesize multi-hop QA trajectories, and validate them with the deployed retriever to obtain executable trajectory-level supervision. We then optimize the retrieval policy with Group Relative Policy Optimization (GRPO) and
arXiv:2608.22452v1 Announce Type: new Abstract: Surprisal, the negative log-probability a language model assigns to a word given its preceding context, reliably predicts adult reading times. Does it contribute as much to explaining when children acquire individual words? Frequency reflects a learner's cumulative exposure to a word, whereas surprisal reflects how predictable a single occurrence is given its context. We investigate this question across two corpus-based studies of Spanish. In Study 1, we modeled age of acquisition (AoA) for 225 Spanish nouns using lexical frequency and contextual diversity from child-directed speech, plus surprisal from three language models differing in architecture and training language (BETO, BERTIN, mGPT). Frequency strongly predicted AoA (r=-.597, p<.001); surprisal added little beyond frequency and word length, including in a naturalistic-context analysis. In Study 2, we modeled adult fixation durations in the Chilean Spanish subsample of the Multil
arXiv:2608.22446v1 Announce Type: new Abstract: Metaphors are figurative use of words for conceptual mapping. Metaphor detection in the legal context has been crucial as metaphors are persuasive juridical means of creating legal meaning and concepts resulting in significant consequences. Metaphorical framing in legal discourse by judges, lawyers, and legislators brings about real-time implications upon individuals and influences judicial decision-making, argumentation and interpretation of laws. This is crucial in Human Rights infringement cases where language determines severity of punishment, public perception and judicial outcomes. While automatic metaphor detection in major languages like English, Spanish, Polish, Lithuanian have aided in understanding inherent intentions of metaphorical use of language, there is no such attempt in low-resource languages like Hindi. The dearth of annotated legal corpora in Hindi makes it difficult to develop NLP models and detect metaphors in judic
arXiv:2608.22444v1 Announce Type: new Abstract: The unit of AI safety evaluation is still the individual model, yet language-model agents are increasingly deployed in interacting populations that read and write one another's decisions. This raises a question no single-agent audit can answer: an agent that is well-calibrated on its own may still be pulled toward a different decision by the agents around it. We study this on a security-triage task, where populations of language-model monitors decide whether to escalate or dismiss alerts, and into which we can inject a committed minority that always pushes one way. We find that two alerts a single agent judges almost identically on its own can drive collective behavior far apart, so auditing any one member need not reveal what the population will do. Yet that collective behavior can be predicted in advance. From a population's benign, adversary-free operation alone, we calibrate a response function that forecasts, before any attack is run
arXiv:2608.22432v1 Announce Type: new Abstract: Multilingual LLM judges produce different evaluator-backbone rankings depending on the prompt language: on an eight-language Agent-as-a-Judge benchmark, the top-ranked backbone alternates across English, Arabic, Chinese, Hindi, Japanese, Spanish, Turkish, and Swahili, and 7 of 15 backbone pairs show statistically significant pairwise rank reversal. We treat this as a measurement problem. The multilingual judge score decomposes additively into task difficulty, backbone skill, and a language-backbone interaction term, the last of which is recoverable without human labels by double-centering the cell-mean score matrix. We make this estimator (\textbf{Consensus-Based Calibration}, CBC) explicit, give an $O(1/\sqrt{n})$ finite-sample concentration bound with variance constant $(1-\tfrac{1}{m})(1-\tfrac{1}{k})$, and show that it is unbiased even when task-language interactions are present. Across 7{,}920 judge runs (6 backbones, 8 languages, 55
arXiv:2608.22411v1 Announce Type: new Abstract: Social interaction increasingly takes place in multicultural settings, where individuals may draw on multiple cultural influences and adapt their communicative behavior across contexts. Despite recent advances in equipping Large Language Models (LLMs) with social understanding capabilities, existing approaches often model culture as a static demographic attribute, limiting their ability to accommodate hybrid and dynamically expressed communicative preferences. Therefore, in this paper, we propose \textbf{DyCAC}, a training-free framework that achieves fluid social alignment by incorporating \underline{Dy}namic \underline{C}ultural \underline{A}daptation with continuous \underline{C}ognitive tracking. Rather than inferring a fixed cultural identity, DyCAC models culturally relevant communicative preferences as a time-varying mixture of population-level cultural reference profiles. This reference-based representation is further calibrated u
arXiv:2608.22390v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong potential in graphical user interface (GUI) generation, but reliable evaluation remains challenging due to uncontrolled data distributions, noisy annotations, and limited layout scenario coverage. To address this, we propose SchemaGUI, a template-based benchmark for controllable GUI generation evaluation. By synthesizing paired natural language instructions and deterministic function-call references from parameterized interface schemas, SchemaGUI can generate thousands of deterministically annotated tasks in seconds without human labeling. Based on 1,000 evaluated instances per scenario and language across six representative bilingual scenarios, we benchmark five mainstream models, including the Qwen3.5 family, Qwen3-Coder-30B, and DeepSeek-R1. Our extensive analysis reveals three key insights. First, precise geometric spatial control remains an important bottleneck; while scaling Qwen
arXiv:2608.22388v1 Announce Type: new Abstract: Propaganda detection includes several related prediction levels, ranging from sentence-level decisions to technique classification and span identification. However, it remains unclear how supervision at these levels interacts when learned jointly across Arabic and English. We present ProBel, an Arabic and English resource that aligns binary labels, multi-label annotations over 23 propaganda techniques grouped into six coarse categories, technique-labeled spans, and reference explanations for the same news sentences. It includes a substantially larger English collection and supports matched binary, coarse-grained, multi-label, and span-level tasks in both languages. We evaluate zero-shot prompting, task-specific fine-tuning, and joint training under a shared setup. A single bilingual multi-task model achieves the best overall performance and remains competitive across tasks and languages. Cross-task analysis shows that transfer depends on
arXiv:2608.22376v1 Announce Type: new Abstract: Large language models generate tokens sequentially, but can they execute multiple tasks concurrently while forming each token? Broader attention allocation may provide a mechanism for such task concurrency. Existing approaches to scaling inference primarily rely on longer generations, more samples, or additional verification stages, while attention dispersion is often treated as a signal of interference or error. Task concurrency within serial generation therefore remains underexplored. We propose the Model Hyper-Threading Hypothesis and evaluate its predictions using multiple coordinated tasks that share state within the same problem. We design three conditions (Baseline, Serial Functional Scheduling, and Concurrent Functional Loading) and evaluate their benefits and costs using accuracy, output-token distributions, and attention metrics. On an AIME 2025 development set, Concurrent Functional Loading achieves the highest accuracy. Relati
arXiv:2608.22367v1 Announce Type: new Abstract: Diffusion multimodal large language models (dMLLMs) frequently produce long-form outputs marred by semantic drift and repetition, with quality generally degrading as output length increases. We identify two structural deficiencies in existing decoding methods as primary drivers of these failures: confidence-based scoring ignores decoded-neighbor support, and block partitioning prevents access to high-readiness semantic anchors, together causing tokens to be committed before their local context is sufficiently established. We propose \ours{} (\textbf{C}ontext-\textbf{A}ware \textbf{C}luster \textbf{D}ecoding), a training-free decoding method that scores each masked position by a multiplicative composite of softmax confidence and neighbor proximity, promoting contextually ready tokens above isolated candidates while suppressing low-confidence positional noise, operating block-free to keep high-readiness anchors globally accessible. \ours{}
arXiv:2608.22339v1 Announce Type: new Abstract: Extracting skills from past successes is critical for the efficient evolution of Large Language Model (LLM) agents. Prevailing agent self-evolution paradigms typically rely on a core assumption: equipping LLMs with skill memories derived from successful trajectories will monotonically improve their problem-solving capabilities. However, probe analyses reveal that extracting skills solely from successful trajectories traps the model in a \textbf{Skill Imitation Trap}. For tasks that resemble past successes but require different tools, retrieving more skills paradoxically increases the model's confidence in wrong tool calls---procedure skills raise the wrong-tool margin by $47\%$ over a memory-free baseline. To overcome this limitation, we propose \textbf{Boundary-Aware Skill Memory} (BASM), which augments each skill with explicit boundary fields---applicability conditions, risk cues, avoidance rules, and recovery notes. These fields transf
arXiv:2608.22335v1 Announce Type: new Abstract: Bengali is the seventh-most-spoken language globally, yet LLM safety evaluation remains overwhelmingly English-centric. We introduce BanglaSafe, a benchmark of 879 Bengali prompts combining 309 natively authored prompts with 570 expert-reviewed prompts, spanning 17 culturally grounded harm categories and five prompting conditions that vary language, writing style, and authority framing. Evaluating 18 frontier LLMs, we find that over half of all responses are unsafe or partially unsafe (53.6%) while 14.7% contains strictly harmful content, and that the strongest observed effect is not the switch from English to Bengali but the choice of writing style within Bengali: the same harmful request phrased as a formal newspaper investigation succeeds 17 percentage points more often than the same request phrased as a casual message, with no adversarial engineering involved. We further show that existing safety classifiers struggle to reliably evalu
arXiv:2608.22332v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate remarkable problem-solving capabilities when guided by Chain-of-Thought (CoT) prompting, yet the internal mechanisms underlying these improvements remain poorly understood. In this work, we investigate where CoT-related causal effects emerge across the generated reasoning trajectory and which attention heads carry signals that contribute to final-answer computation. Because CoT reasoning unfolds over multiple generated tokens, standard activation patching at a single static token position is insufficient to characterize these temporally distributed effects. To address this limitation, we introduce a sequential activation patching framework that traces CoT-conditioned attention-head activations across token positions and aggregates their effects using Part-of-Speech-guided analysis. We further introduce Sequential Multi-Head Patching to evaluate the joint contribution of distributed head sets, toget
arXiv:2608.22331v1 Announce Type: new Abstract: We audit measurement variability for 3 native tool-calling endpoints across 2 providers on the official BFCL multiple and parallel categories, using matched AST grading. At temperature 0, reruns are nearly deterministic across Groq endpoints and a thinking-enabled Gemini setting: ever-flip fractions are 0.7%, 2.0%, and 2.7%, with mean run correlations of 0.997, 0.966, and 0.961. Semantics-preserving prompt perturbations create the larger floor on all endpoints, with median perturbation paired SDs 11x to 58x larger than rerun paired SDs. The failure character also shifts: malformed-output failures account for 30%, 7%, and <1% of task failures, so marginal accuracy hides not only stability but also failure mode.
arXiv:2608.22321v1 Announce Type: new Abstract: Multimodal time-series forecasting has emerged as a promising paradigm in which natural-language context is expected to improve predictive performance. Recent multimodal foundation models, including Aurora, as well as early- and late-fusion approaches such as MM-TSFlib and TaTS, report substantial gains over unimodal baselines on the Time-MMD benchmark, attributing these improvements to textual information. However, whether these models are actually sensitive to the semantic content of the text remains unverified. We address this question through controlled text perturbations, attribution analyses, and probes of Aurora's text pathway. On Time-MMD, swapping each row's text for any other real text (empty, constant, within-domain shuffled, or cross-domain) moves mean MSE by less than $0.5\%$ on all three architectures. The improvement reported in the literature is recovered when a co-shipped numeric column is removed without touching text. W
arXiv:2608.22312v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains vulnerable to jailbreak attacks. A key challenge is that safety behavior learned in the textual space does not reliably transfer to fused cross-modal representations, leaving multimodal inputs exploitable through latent semantic cues. We propose Text-Anchored Semantic Perturbation Attack (TA-SPA), a black-box jailbreak framework that optimizes transferable perturbations in a text-anchored semantic space. TA-SPA integrates Text-Anchored Semantic Factorization (TASF), which encourages the separation of cross-modal semantic factors from modality-specific residuals, with Semantic-Preserving Augmentation (SPA), which diversifies harmful target anchors while preserving semantic consistency. Experiments show strong attack effectiveness and transfer to commercial MLLMs, with competitive performance under re
arXiv:2608.22295v1 Announce Type: new Abstract: Evaluation of large language models (LLMs) increasingly requires predicting how a model will perform on new questions or tasks before collecting large amounts of new annotations. This problem is challenging because question difficulty, scenario, and underlying capability demands can vary substantially. Simple retrospective averages may confound model ability with item characteristics. In this paper, we study a model-based evaluation framework that combines multidimensional item response theory model with question contexts to predict LLM performance on unseen questions. The framework represents LLMs through latent capability profiles while using question content to inform item characteristics, allowing information to transfer beyond previously observed items. Empirically, we find that for within-scenario evaluation, incorporating question embeddings improves prediction relative to model-free baselines, and that multidimensional latent stru
arXiv:2608.22274v1 Announce Type: new Abstract: Machine translation tests masked diffusion language models (dLLMs) because every source token must be rendered faithfully, while fixed canvas decoding must choose target length before denoising. Existing masked diffusion decoding work mainly studies token unmasking order, leaving this length decision under-explored despite its direct effect on coverage and redundancy. We introduce Entropy-Valley (EV), a training-free length selector that scores candidate target canvases by mean predictive entropy from all-mask forward passes and selects the canvas the backbone is most prepared to fill. Relative to a baseline using training corpus length statistics, EV recovers 64.9%, 65.3%, and 33.0% of the COMET-22 gain from reference target lengths on En$\to$Zh, Zh$\to$En, and En$\to$De. Our diagnostics show that denoising-friendly lengths need not match reference lengths. Evaluation by three translation experts supports the En$\leftrightarrow$Zh adequa
arXiv:2608.22246v1 Announce Type: new Abstract: Harmful content in German social media does real-world damage, from calls to action to criminal defamation. The GermEval 2026 shared task scores its detection in four subtasks. The technical challenge is a severe class imbalance. The harmful classes are rare and share surface language with the dominant majority class, yet under macro-F1 they decide the score. The decisive lever is then not a stronger single model but error independence. This insight becomes a per-subtask nine-voter ensemble spanning three orthogonal axes: LLM, training method and class scope. Selected mainly on internal cross-validation, the system reaches macro-F1 of 89.56 (C2A), 71.63 (DBO), 54.84 (VIO) and 83.02 (DEF) on the hidden test set, placing first on all four subtasks.
arXiv:2608.22244v1 Announce Type: new Abstract: Flow-matching language models refine all token positions in parallel and can trade sampling steps for latency, yet generation quality still degrades sharply with few sampling steps. We trace a source of this degradation to a train--inference mismatch in previous-prediction self-conditioning: during training, the self-conditioning input is computed from the current noisy state with no intervening solver step; during sampling, the solver folds the previous prediction into the latent before that same prediction reappears as the explicit self-conditioning input. This coupling, absent during training, creates redundancy that grows with step width. We show that the mismatch degrades both the self-conditioning input and the solver update, and derive a correction for each from the model's own structure. From the frozen projection weights we identify directions along which the self-conditioning input is redundant with the latent and dampen them; f
arXiv:2608.22230v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for hate speech moderation, often within human--AI workflows in which reviewers provide feedback before a final decision. Such feedback introduces two manipulation directions: whitewashing hateful content as normal and smearing normal content as hateful. This study examines the susceptibility of initially correct model judgments to annotator-style rebuttals and analyzes whether attack effectiveness differs across manipulation directions. We introduce a rejudge protocol that extends direct contradiction with decision-boundary perturbations and adversarial rationales. Experiments with multiple LLMs on two hate speech datasets show that annotator-style rebuttals substantially degrade moderation performance, with stronger effects in multi-turn settings. The results further reveal stable, model-specific asymmetries between whitewashing and smearing across attack configurations, indicating dist
arXiv:2608.22229v1 Announce Type: new Abstract: Normative rules like institutional charters and workplace policies must be both human-readable and operationally verifiable against actual environment records. However, current language generation and structured-output benchmarks primarily reward surface fluency or schema compliance, leaving operational grounding weakly tested. This creates a critical vulnerability where standard language models generate plausible-sounding policies that fail during enforcement because they rely on unavailable data logs or misaligned scopes. To address this challenge, we formalize the problem as Grounded Normative Rule Synthesis (GNRS) and introduce GNRS-Search, a framework that utilizes Markov Chain Monte Carlo (MCMC) sampling to optimize a discrete, five-slot And-Or Graph (AOG). By explicitly decoupling intermediate operational structure from final prose generation, this method isolates executable feasibility from writing style and allows rule failures t