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:2607.16259v1 Announce Type: cross Abstract: Pretrained models are typically ranked on multi-task leaderboards to assess their effectiveness across diverse tasks. Rank confidence intervals were recently introduced as a method to quantify the uncertainty in these rankings by aggregating pairwise hypothesis tests. In this work, we analyze the sources of uncertainty in the knowledge evaluation benchmark MMLU and show how hypothesis tests can be modified to account for their effects. We demonstrate that ranking variability across MMLU subjects is substantial and should be considered when comparing LLMs or identifying the top-performing models.
arXiv:2607.16257v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a widely adopted technique for improving large language models (LLMs) on complex tasks. Despite this progress, existing RL methods still face challenges in training agents with longer-horizon interactions. One major bottleneck is distinguishing the contribution of different actions in long-horizon interaction, leading to high optimization variance. To address this, we introduce a novel policy gradient method, Hindsight Policy Optimization (HPO), that projects both the current policy distribution and the hindsight distribution into an intent space and extracts low-variance learning signals from the Wasserstein distance between them. We theoretically and empirically show that aggregating semantically similar states and actions in the intent space yields a bounded-variance estimator and improves policy performance stably. Our code is available online.
arXiv:2607.16255v1 Announce Type: cross Abstract: A crucial step in machine learning pipelines is to present each entity with features or attributes that are representative of the characteristics of the processed entities. Feature engineering is an important step in finding a relation among attributes that otherwise may not be processed by the ML algorithms. Meanwhile, Large Language Models have shown promising abilities in coding, mathematical reasoning, and processing world knowledge. In this work, we utilize an LLM for the problem of feature generation from tabular data based on the previously given features. We have created a pipeline that takes a set of attributes and a prompt to generate new features. Then, our selection algorithm selects the best-performing sets of attributes. We apply our method to eight datasets from different domains and data types. Our results show that, in most cases, the language model can produce new features based on mathematical and logical operators th
arXiv:2607.16244v1 Announce Type: cross Abstract: Training multi-turn evidence-reading agents with outcome-only reinforcement learning is unstable because intermediate turns receive little direct credit. In HotpotQA experiments with Qwen2.5-3B-Instruct, GRPO initially improves (standard F1 0.430) but subsequently collapses to 100% format-violating outputs. Training-log diagnosis reveals a zero-advantage lock-in mechanism: all sampled trajectories receive the minimum format penalty (-2.0), group-relative advantages vanish, and the policy-gradient loss becomes zero--an optimization deadlock. We propose a variance-injection strategy: by assigning per-turn rewards to intermediate evidence-reading turns, we prevent the group reward distribution from collapsing to a single value--preserving the variation that GRPO's group-relative advantage requires. Contextual Information-Gain Policy Optimization (CIGPO) implements this strategy using the marginal increase in the frozen reference model's lo
arXiv:2607.16215v1 Announce Type: cross Abstract: Existing guardrail systems for large language model agents operate as binary classifiers that block unsafe content, leaving organizations to discard failing outputs and retry from scratch. We introduce RAIL Guard, a closed-loop responsible AI pipeline that evaluates LLM outputs across eight measurable dimensions and iteratively remediates failing outputs through an evaluate-rewrite-reevaluate loop. We evaluate the pipeline across three experiments on four frontier LLMs and 4,276 content outputs plus 6,400 agent tool-call scenarios. Closed-loop remediation achieves 96.9% convergence versus 49.1% for block-and-retry, though the highest-convergence method reduces utility by 22.3%; feedback-driven self-repair achieves 86.6% convergence on fixable dimensions with no significant utility loss (p = 0.177). Pre-tool-call evaluation reduces unsafe agent executions by 33% (p = 0.007) with zero impact on task completion. We identify a key distincti
arXiv:2607.16208v1 Announce Type: cross Abstract: Graph-grounded multimodal question answering organizes text, tables, and images in a structured evidence graph, yet end-to-end accuracy depends on which multimodal assets are ranked highly enough to enter downstream reasoning; for graph-linked images, single-vector bi-encoder similarity can discard patch- and token-level structure needed for fine-grained alignment. We evaluate replacing the visual candidate-ranking operator over graph-linked image nodes with late-interaction MaxSim-style multi-vector scoring in the ColBERT/ColPali lineage, while keeping offline graph construction, text- and table-side retrieval, structured extraction, and downstream reasoning unchanged. On MultimodalQA, this change is associated with improved retrieval-stage point estimates for graph-linked image candidates and downstream QA gains, with larger movement where visual evidence matters most and mixed trends on text-dominant questions; we interpret the patte
arXiv:2607.16203v1 Announce Type: cross Abstract: Document parsing is a foundational step for document understanding tasks such as visual question answering and key information extraction, as it transforms unstructured scanned images into structured representations by extracting textual, visual, and layout information. While numerous Optical Character Recognition (OCR) engines and multimodal large language models (MLLMs) have been developed for this purpose, selecting an appropriate document parsing solution for a given document collection remains challenging, particularly in label-scarce settings. In this work, we conduct a systematic evaluation of text recognition performance across a diverse set of OCR engines and state-of-the-art MLLMs on multiple scanned document benchmarks spanning different domains and languages. Motivated by the limited contextual reasoning capabilities of many OCR engines and the high cost of manual annotations, we propose DocOCR-Eval, an annotation-free evalu
arXiv:2607.18235v1 Announce Type: new Abstract: Autonomous discovery systems such as OpenEvolve and TTT-Discover are often used as general-purpose harnesses. However, in practice these are composite systems combining several design choices about archives, parent selection, exploration, and budget allocation into a single recipe. Because discovery runs are expensive and inherently stochastic, existing harnesses are often compared using too few independent trials to distinguish key methodological improvements from run-to-run variance. We systematically decompose OpenEvolve-style evolutionary search and the TTT-Discover search harness into its constituent components and systematically evaluate 30 budget-matched harnesses across 12 model-problem pairs using more than 3.1 million LLM rollouts and repeated-trial statistical analysis. Our results show that discovery harnesses have a generalization problem: No fixed harness is reliably superior across the evaluated model-problem pairs, and var
arXiv:2607.18232v1 Announce Type: new Abstract: Users frequently express their beliefs to large language models (LLMs). In some situations, the LLM should accept these contextual beliefs as true. In others, they should stick to their prior knowledge. Notably, users' expressions of belief (EoBs) can take linguistically diverse forms - using presuppositions, evidential and certainty markers, or varied tones - each of which may have a different persuasiveness over the LLMs. We introduce a typology to systematically evaluate how different EoBs affect whether models follow context versus prior knowledge. The typology is grounded in four linguistically motivated dimensions: form, evidentiality, epistemic stance, and tone, spanning 17 fine-grained types. By pairing these EoBs with world knowledge facts, we generate controlled EoB-query pairs that isolate the effect of linguistic variation. Using this benchmark, we evaluate 16 LLMs that differ in architecture (Llama3, Qwen3, Gemma3), scale (1B
arXiv:2607.18213v1 Announce Type: new Abstract: Pruning long context for coding agents has been a vital technology for efficient context management. While existing context pruning methods such as SWE-Pruner realize this by attaching a separate code classifier, we find the agent itself encodes internal representations indicating the relevance of code context when reading tool output. Based on this finding, we propose SWE-Pruner Pro, which prunes tool outputs directly inside the agent. Concretely, a small head turns the agent's own internal representations into a keep-or-prune label for each line, with a length-aware embedding keyed to each tool output's line count. Across two open-weight backbones and four multi-turn benchmarks, SWE-Pruner Pro saves up to 39% of prompt and completion tokens while preserving task quality, with bounded inference overhead. Notably, on MiMo-V2-Flash SWE-Pruner Pro additionally raises the SWE-Bench Verified resolve rate by +3.8% and the long-context Oolong a
arXiv:2607.18199v1 Announce Type: new Abstract: Not all training samples contribute equally to large language model fine-tuning. Selecting informative training samples can reduce the computational cost while preserving downstream performance. Many existing data selection methods rely on indirect heuristics, such as data quality, diversity or reasoning trace length. However, the effectiveness of these fixed criteria is task-dependent and difficult to generalize across diverse downstream tasks. Perplexity-based data selection provides a simple and model-aware solution to estimate the sample difficulty, but existing approaches typically score the entire training sequence and ignore the difference in learning objectives of language modeling and reasoning tasks. In this paper, we propose PPL-Factory, a simple and interpretable data selection framework that combines task-aware perplexity-based scores and data budget-aware selection criteria. Experiments on GSM8K demonstrate that PPL-Factory
arXiv:2607.18181v1 Announce Type: new Abstract: Battery-free Internet of Things (IoT) requires iterative design of vibration energy harvesters (VEHs) under coupled physical constraints, while LLMs are emerging as interface layers for engineering workflows. However, existing engineering benchmarks primarily assess final artifact validity, offering limited insights into how LLMs behave across different stages of coupled physical design. We introduce VEHBench, an engineering-native diagnostic benchmark for LLM-assisted VEH design, featuring 763 literature-grounded tasks scored by an analytical physical oracle. VEHBench evaluates four design roles: specification triage, verifier-guided search, corrupted-state recovery, and policy-conditioned selection. Experimental results reveal that LLM capability is strongly stage-dependent: no single model consistently dominates the entire workflow, and response-control profiles expose distinct behavioral patterns across design roles. VEHBench thus pro
arXiv:2607.18114v1 Announce Type: new Abstract: Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant turn often flips an originally correct answer. We study where this susceptibility, spanning sycophancy and related cue-induced biases, lives inside the model. Across five model families and seven BCT bias types, we extract a per-bias direction from hidden states and triangulate it through three measures: probing, leave-one-dataset-out transfer, and causal intervention. The susceptibility is largely installed by alignment tuning rather than pretraining: pretrained base models barely cave to these biases, and their activations carry no cue-specific signal beyond question content. Within aligned models, each bias becomes a single coherent direction that we can both decode and steer along, recovering the unbiased answer across every family we test. The biases stay
arXiv:2607.18098v1 Announce Type: new Abstract: Large language models are increasingly used in practical systems, making efficient model selection important for reducing deployment cost. LLM routing has emerged as a practical solution for allocating each input query to an appropriate model under a desired cost-performance trade-off. Existing routing methods often estimate model suitability from the surface semantics or embedding similarity of the input query. However, such methods may ignore the underlying difficulty of a query, leading to suboptimal routing decisions. To address the challenge, we propose VDAR-Router, a difficulty-aware retrieval-based routing framework. For each input query, VDAR-Router first generates an explicit difficulty analysis. It then retrieves historical examples with similar difficulty profiles. Based on the retrieved records, it estimates candidate model suitability and selects the model using a reward function that considers both performance and cost. Expe
arXiv:2607.18076v1 Announce Type: new Abstract: This study investigates silence gaps in two kinds of audiovisual material. We analysed thirty US situational comedies and fifty-one synthetic podcasts generated with Google NotebookLM. Gaps were compared across speaker gender, assigned from a fundamental-frequency threshold estimated in Praat, and across production settings.
arXiv:2607.18066v1 Announce Type: new Abstract: The value alignment of large language models (LLMs) is crucial for ensuring responses align with human intention and value preferences. However, most evaluations of value alignment focus on Western or universal values, while assessments grounded in the value systems of specific countries remain scarce. In this paper, we introduce Pancasila-Dilemmas, an evaluation dataset of 1,834 questions derived from Indonesian news, classified by 5 values of Pancasila: Religion, Humanity, Unity, Democracy, and Social Justice. This dataset reflects daily life in Indonesia, making it suitable for measuring the value alignment of LLMs deployed for Indonesia. To ensure a more rigorous evaluation, we choose scenarios containing dilemmas. The dataset is proofread by native speakers and answered by 5 diverse Indonesian citizens. We evaluate 50 closed- and open-source LLMs on our dataset. Results reveal that all evaluated LLMs achieves less than 0.5 Probabilit
arXiv:2607.18056v1 Announce Type: new Abstract: Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the biological risks of frontier models, we develop Intern-BioBreaker, a specialized bio-red-teaming model, together with an integrated computational-to-physical framework that couples model-level stress testing with wet-lab validation. Within this framework, Intern-BioBreaker generates targeted jailbreak prompts to test whether aligned models can be induced to provide operational guidance for safety-sensitive biological tasks or produce sequence-level outputs with potentially harmful properties. Selected sequence outputs are then carried forward for DNA synthesis, host expression, and orthogonal protein verification to assess whether model-generated designs can yield the intended biological products. Our evaluation reveals a concerning gap between text-level safeg
arXiv:2607.17952v1 Announce Type: new Abstract: Climate disclosure classification is a fundamental task for analysing corporate climate disclosures, yet such disclosures appear in many different sources -- annual reports, press releases, and earnings calls -- that differ in length, purpose, and writing style. Existing evaluations are mostly conducted within a single source, leaving open whether common LLM adaptation strategies remain effective under source shift. We reframe climate disclosure classification as a cross-source adaptation problem and study three widely used adaptation strategies -- definitions, examples, and fine-tuning -- across eleven open- and closed-source LLMs, using two corpora that share the same label space but come from different sources. We find that all strategies bring positive cross-source gains on average, but the strongest in-source strategies are not the strongest cross-source ones: similarity-based retrieval and LoRA fine-tuning gain most in-source but lo
arXiv:2607.17935v1 Announce Type: new Abstract: Automated fact-checking remains a challenge for Large Language Models (LLMs) due to "query brittleness" in traditional retrieval systems. We propose DeLIVeR (Decomposed Learning for Information-grounded Veracity Recognition), a framework that treats evidence retrieval as a reinforced strategic exploration task. DeLIVeR utilizes a Planner LLM to decompose complex claims into targeted question sets, which are used to traverse structured Knowledge Graphs (KGs) for high-precision evidence. We optimize the Planner's policy using Group Relative Policy Optimization (GRPO) with a reward system prioritizing structural diversity and verdict accuracy. Our evaluation on LIAR, FEVER, and PolitiFact shows that DeLIVeR significantly outperforms state-of-the-art baselines. Using Qwen2.5-7B, our framework achieved peak F1-scores of 83.73, 84.57, and 79.70 respectively, representing a 10-15% improvement over HippoRAG2. By shifting to a reinforced question-
arXiv:2607.17883v1 Announce Type: new Abstract: Enterprises will not deploy AI agents they cannot trust, and the most-cited reason for distrust is hallucination: confident, fluent output that is simply not true. The common response is to wait for a model that does not hallucinate. We argue that this is the wrong target. Large language models are, by construction, capable of generating unsupported text, and no amount of scale removes the possibility; a faithfulness judge bolted onto a raw model catches some errors but still ships others, and even well-curated retrieval pipelines have been shown to fabricate citations. We reframe the goal: "zero hallucination" is not a property a model possesses but a property a system enforces. We present HALO (Hallucination-Aware Layered Oversight), an assurance architecture which treats hallucination as a containable failure mode rather than an eliminable one. HALO composes six layers of defense: grounded generation over retrieved, approved content; c
arXiv:2607.17828v1 Announce Type: new Abstract: Many Bangla words are at once personal names and culturally loaded common nouns, "Maya" is both a girl's name and a word for affectionate compassion. Choosing the right reading demands cultural knowledge that is scarce in the pretraining data of modern language models. We introduce Culturally Entangled Homograph (CEH) disambiguation and build a Bangla benchmark of 1,516 expert-verified sentences (3,032 labelled occurrences) in which one word appears twice with two distinct readings, each labelled with a culturally grounded category and an explanation of the reasoning behind it. Across open- and closed-source models, we find a systematic dominant-meaning bias: models default to the common-noun sense and overlook the name. A Bangla-specific model fails under every prompting regime we test, showing that language-specific pretraining alone does not confer cultural grounding. We further show that contrastive chain-of-thought prompting can shar
arXiv:2607.17812v1 Announce Type: new Abstract: As large audio language models (LALMs) advance, robust evaluation frameworks have become essential. In this context, Spanish speech understanding under realistic acoustic conditions has received particularly little attention. We introduce ESCUCHA, the first Spanish speech understanding benchmark designed to evaluate LALMs across heterogeneous acoustic conditions and reasoning abilities. ESCUCHA comprises 1,000 human-curated questions paired with audio, totaling 162.9 hours sourced directly ``from the wild'' rather than drawn from existing datasets, with durations ranging from a few seconds to over 80 minutes. The benchmark emphasizes reasoning, spanning 9 perceptual and 10 reasoning categories, and it captures linguistic diversity through multiple Spanish accents and non-normative speech. ESCUCHA further includes multi-audio questions, spoken questions, and audio instructions, and it flags which questions support open-ended evaluation. Be
arXiv:2607.17766v1 Announce Type: new Abstract: Extra context is valuable for simultaneous speech translation of technical talks, but injecting the entire document context into every streaming segment is often too coarse. Through diagnostic experiments, we find that context gains mainly come from paper-specific terminology recovery rather than uniform semantic enhancement. We therefore propose EGTA, an Evidence-Grounded Terminology Adaptation framework that builds a document terminology memory, selects compact candidate terms conditioned on the current streaming state, and adapts ASR/speech-side and decoder-side decision spaces using only the selected terms. EGTA can be instantiated in cascaded, end-to-end, and generation-only SimulST settings without full-model fine-tuning. We evaluate EGTA on an ACL technical-talk SimulST evaluation suite consisting of MCIF-dev and ACL60/60-dev. On MCIF-dev, EGTA-RG improves BLEU by +1.05/+0.59, XCOMET-XL by +0.019/+0.006, named-entity recall by +79\
arXiv:2607.17738v1 Announce Type: new Abstract: Citation function classification plays a crucial role in understanding the relationships between scientific publications and advancing bibliometric analysis. This study presents one of the first comprehensive evaluations of multiple state-of-the-art (SOTA) large language models (LLMs) for citation function classification, achieving new SOTA results on the ACL-ARC dataset. We systematically compare five models (Mistral 7B, Orca 2-7B, LLaMA 3.1-8B, Falcon 7B, and SciBERT) across zero-shot, few-shot, and fine-tuning approaches. Our fine-tuned Falcon 7B model achieves a 73.3% macro F1 score on ACL-ARC, representing a significant improvement over previous methods. Additionally, we introduce AC3, a novel dataset featuring a seven-category annotation scheme that distinguishes between neutral acknowledgments and explicit evaluative stances (more opinion-oriented citations - criticizing, complimenting, contradicting). The dataset is implemented ac
arXiv:2607.17715v1 Announce Type: new Abstract: Long-context inference is central to modern large language model (LLM) applications such as retrieval-augmented generation and multi-document reasoning. To mitigate the growing inference cost, recent work has explored key-value (KV) cache reuse to reduce redundant prefill computation. However, existing reuse methods primarily focus on computation savings and overlook a critical bottleneck in long-context LLM serving: the cost of storing and accessing large KV caches. While KV compression appears to be a natural complement, naively combining compression with non-prefix KV reuse often leads to severe accuracy degradation. In this work, we propose C$^2$KV, a unified framework for non-prefix KV reuse that jointly optimizes KV extraction and inference-time concatenation. C$^2$KV learns a composable and compressed KV cache manifold that is explicitly designed to be position-agnostic. Our approach introduces a lightweight sidecar Extractor with
arXiv:2607.17713v1 Announce Type: new Abstract: Span-level rationales are often assumed to improve controllability in text detoxification, but it remains unclear when such guidance helps and when it introduces trade-offs. We present Awareness-Enhanced Guidance for Iterative Safeguard (AEGIS) as an exploratory framework for studying span-guided multilingual detoxification across English, Mandarin Chinese, and Korean. AEGIS combines span-level detector outputs with frozen generator backbones, allowing harmful spans, intensity labels, and target attributes to be provided as structured guidance during rewriting. Rather than claiming state-of-the-art detoxification performance, we analyze how span guidance affects the balance between toxicity reduction and meaning preservation across generator families, model scales, and languages. Our results suggest that span-guided detoxification is conditionally useful: explicit rationales change the trade-off between toxicity reduction and meaning pres
arXiv:2607.17689v1 Announce Type: new Abstract: Multilingual language models rely on shared subword vocabularies to represent multiple languages within a limited number of token units. While such sharing is often useful, it can also create cases in which identical surface forms are treated too uniformly across languages, even when their meanings or usage differ. We investigate this limitation through cross-lingual homographs and false friends, and examine whether introducing language information earlier in the tokenization process can improve their treatment. We propose a simple tokenizer-level intervention based on language cues: language-specific characters replacing initial characters of shared-vocabulary words, reducing common identity during vocabulary construction. In intrinsic analysis, we find through tokenizer-level statistics that BPE and UnigramLM often treat cross-lingual homographs in a largely language agnostic way, whereas the context-sensitive SaGe tokenizer diverges mo
arXiv:2607.17531v1 Announce Type: new Abstract: Test-time collaboration, including self-consistency, best-of-N selection, critic models, and verifier pipelines, is often credited with broadly improving LLM reasoning, yet its gains are uneven and sometimes negative. We ask when training-free collaboration should be expected to help. For a fixed candidate pool, we decompose a selector or verifier's net gain into measurable factors: recoverable mass, verification-signal coverage, conditional selection quality, and harm to already-correct outputs. This reframes collaboration as a candidate-selection problem rather than as an intrinsic property of a multi-agent topology. Across LiveCodeBench, MATH Level-5 hard subjects, and GPQA-Diamond, gains are bounded first by the oracle gap and then by signal fidelity, which we measure directly as candidate-level agreement between verifier verdicts and official labels. On LiveCodeBench, a public-test verifier (MCC 0.825) gains +8.14 percentage points (
arXiv:2607.17524v1 Announce Type: new Abstract: We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task. Our key intuition is that by training the model to distinguish good and bad tokens in a response, we naturally guide the model towards generating good tokens, while avoiding the pitfalls that come with directly training the model to generate off-policy tokens. Experiments on document summarization tasks show that TOPL achieves strong out-of-distribution generalization across 11 datasets against a diverse set of sequence-level and token-level baselines. We further demonstrate that TOPL transfers effectively to machine translation, suggesting that its benefits generalize across different faithful generation tasks. Through ablation studies, we confirm that our token-level learning signal is critical to good performance; sequence-level analogues do not confer similar benefits. Finally, we
arXiv:2607.17466v1 Announce Type: new Abstract: Multilingual assessment systems commonly rely on translation for scoring and quality-control processes. We evaluate whether multilingual sentence embeddings can replace translated English input for Linguistic-Integrated Reliability Auditing (LiRA) across 11 PIRLS constructed-response items and three embedding models. Native-language embeddings reproduced translation-based reliability estimates closely while recovering responses excluded after translation failure, with no meaningful change in reliability.
arXiv:2607.17452v1 Announce Type: new Abstract: Measuring conversational states such as cognitive load and conversational power from multimodal behavior requires characteristic features that are not only predictive but also reliable across task contexts. We present a three-dimensional evaluation framework assessing predictive accuracy, cross-task generalizability, and test-retest reliability, applied to interactional, acoustic, and linguistic features extracted from dyadic conversations during collaborative tasks performed over a video-conferencing platform (AVCAffe dataset; 53 dyads, 9 tasks). Our results show that no single feature family dominates all three dimensions. Linguistic features show the highest predictive accuracy for cognitive load but collapse under cross-task evaluation, revealing sensitivity to task-specific vocabulary. Additionally, acoustic reliability, often reported as evidence of feature stability, degrades once speaker identity is controlled, confirming that sta
arXiv:2607.17420v1 Announce Type: new Abstract: Biographical personas are widely used in system prompts, but their effects on code generation are rarely evaluated under controlled, pre-registered conditions. We tested four prompt conditions (no persona, two engineer personas, and a research-librarian persona), 12 code-generation tasks, two frontier models, and five runs per cell (480 completions). Persona effects differed between the two tested models. Under the pre-registered mixed-effects analysis, the condition-by-model interaction was significant for provider-reported output tokens; a post-hoc visible-character measure showed the same qualitative pattern. Six GPT-5.5 completions were length-capped and are reported separately. On Claude Opus, the minimalist engineer persona reduced visible output by 30% (33% in provider tokens) without improving correctness, while the thorough engineer persona increased output without a correctness gain. In an exploratory post-hoc analysis, the libr
arXiv:2607.17382v1 Announce Type: new Abstract: Existing research shows that AI-generated text detection classifiers achieve strong in-distribution (ID) performance but do not maintain the same performance on out-of-distribution (OOD) texts, suggesting overfitting to dataset-specific features. However, combining different training datasets doesn't always improve performance and, in some cases, can even encourage shortcut learning. To address this issue, we fine-tune BERT-tiny models with Bayesian classification heads to select texts across three different datasets to use as a consolidated training set. We trained three different classifiers: fine-tuned DeBERTa-V3-large and ModernBERT-large classifiers via empirical X-risk minimization, and an MCGrad model that calibrates the predictions from the ModernBERT-large classifier. The DeBERTa-V3-large-large classifier achieves a mean score of 0.882 on the PAN 2026 test set across five metrics: AUROC, $F_1$, C@1, Brier score, and $F_{0.5u}$. M
arXiv:2607.17266v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing. However, LLMs often suffer from hallucinations and lack of relevant knowledge when dealing with question answering (QA) tasks. To mitigate these issues, knowledge graphs (KGs) have been utilized to enhance LLM reasoning. Nevertheless, KGs often contain noise and errors, while existing KG-enhanced LLM approaches are generally unable to identify and filter such noisy and erroneous content, which can instead amplify hallucinations and pose challenges for reliable reasoning. Uncertain knowledge graphs (UKGs), which associate each triple with a confidence score to quantify uncertainty, offer a promising direction to address this challenge. Compared with prior work, we investigate how to leverage UKGs to support LLMs for QA. We propose Debate-on-Graph (DoG), a new framework that enables LLMs and UKGs to collaborate adaptively for reliable reas
arXiv:2607.17262v1 Announce Type: new Abstract: Existing methods for multimodal sentiment analysis (MSA) under missing modalities usually follow a repair-first paradigm. We revisit this assumption and ask: \emph{should every missing modality be repaired?} A per-sample oracle analysis shows the answer is not always: full-modality input is optimal for only a small fraction of samples, and every modality subset is preferred by some samples. These results suggest that adding or repairing modalities may not always improve prediction, and that the utility of each modality is sample-dependent. Building on this finding, we propose \textbf{S}ufficiency-\textbf{I}nformed \textbf{E}vidential \textbf{V}al\textbf{vE} (\textbf{SIEVE}) that turns ``whether to repair'' into an explicit, learnable decision at the sample level. SIEVE compares a direct prediction branch with a repair branch, derives an empirical sufficiency signal from their per-sample loss gap, and routes each input through an evidentia
arXiv:2607.17250v1 Announce Type: new Abstract: This paper introduces EvolvingWorld, a framework and benchmark for character and world co-evolution in interactive literary worlds. Existing systems either treat interactive literary simulation as static persona imitation or isolated scene generation, failing to capture how characters and worlds evolve together over time. To address this, EvolvingWorld models literary simulation as a long-horizon process where characters interact, scenes progress, and character and world states are persistently updated. Unlike prior systems relying on fixed schemas, EvolvingWorld adopts an open-schema framework to support simulation across diverse literary worlds. The framework consists of two coupled modules: a Character Agent for multi-character role-play and persistent profile evolution, and an LLM-based World Model for global and location/entity-level state maintenance and scene progression. Based on this architecture, we formulate 7 trainable tasks f
arXiv:2607.17237v1 Announce Type: new Abstract: AI_LectureNote is a historical, readability-oriented post-ASR workflow for Korean-English medical lectures. It rewrites speech-to-text output into study transcripts while restoring Latin-script medical terms rather than Korean phonetic transliterations. We retrospectively evaluate the workflow on four author-recorded lectures across five conditions. In this pilot, post-processing raised the macro English-script rendering rate from 0.39 to 0.71 on the whisper-1 path and from 0.26 to 0.65 when applied to 3-minute chunked gpt-4o-transcribe output. However, English-script rendering did not imply semantic faithfulness: the two post-processed conditions showed semantic drift in 34 and 36 of 282 reference sentences and polarity failures in 11 and 13 of 101 polarity-cue rows. A descriptive cross-input comparison suggested different candidate failure patterns: polarity-failure sets overlapped more strongly across front-ends (Jaccard 0.60; 9 shared
arXiv:2607.17230v1 Announce Type: new Abstract: This paper describes TalTech's submissions to the Beyond Transcription Challenge (BeTraC), which requires generating SOAP notes directly from long doctor-patient conversation recordings, without intermediate transcription. After screening open-weight speech LLMs for long-audio robustness, we adapted Voxtral Mini (lightweight track) and Voxtral Small (heavyweight track) with LoRA supervised fine-tuning followed by DAPO reinforcement learning that uses the challenge metric, Open Medical Concept F1, as its reward. Our systems ranked first in both tracks, and an independent LLM-as-a-judge evaluation showed the lowest hallucination rate among all submissions, indicating that reinforcement learning against a concept-matching metric need not compromise factual reliability. We also find that fine-tuning on text transcripts transfers well to speech input and appears to improve robustness on out-of-domain real recordings.
arXiv:2607.17228v1 Announce Type: new Abstract: Prior work on LLM-generated text has demonstrated quantitative and qualitative departures from text produced by humans. LLM-generated texts differ from human writing in style, resulting in a characteristic textual "feel," while the semantic range of LLMs is much restricted compared to that of humans. In this contribution, I note simple but consistent patterns in the statistical distribution of n-grams within LLM-generated text. Via qualitative analysis of these n-grams, I reveal deficiencies in LLM style. Because higher-order n-grams correlate to semantic content, I conclude that questions of style and semantics are not cleanly separable.
arXiv:2607.17219v1 Announce Type: new Abstract: Human survey respondents exhibit question-order effects that satisfy the QQ (quantum question) equality, an a priori, parameter-free prediction of the projective quantum question-order model. We develop the QQ equality into an audit criterion for sequential judgments of autoregressive large language models (LLMs). Theoretically, we characterize which mechanism classes satisfy it robustly: marginal-independent kernels satisfy QQ iff all four mismatch transition rates coincide (a class containing the 2D rank-1 projective model with a fixed measurement pair under state variation); a polarity- and position-dependent repetition family is characterized by an exact cross-symmetry condition with closed-form violations; QQ-satisfying behaviors are closed under order-matched mixing; and the rank-2 Contextuality-by-Default criterion translates into audit coordinates as $|\qQQ|\le\OSS$, where $\OSS$ (the order-sensitivity score) totals the order sens
arXiv:2607.17173v1 Announce Type: new Abstract: Evaluating large language models (LLMs) across languages remains challenging, as most multilingual benchmarks rely on translated English datasets, often obscuring linguistic and cultural specificity in the target language. This issue is particularly pronounced for less-resourced languages such as Kyrgyz, where reliable natively authored evaluation data are scarce. Building on previously introduced Kyrgyz-language evaluation datasets, this work reports the first systematic and large-scale evaluation of LLMs in Kyrgyz using the KyrgyzLLM-Bench benchmark suite. KyrgyzLLM-Bench comprises two natively authored datasets$-$KyrgyzMMLU and KyrgyzRC$-$together with carefully translated and manually post-edited versions of WinoGrande, HellaSwag, BoolQ, and TruthfulQA. We evaluate 26 open- and closed-source LLMs under zero-shot and few-shot settings, analyzing model performance, cross-lingual transfer, and the impact of translation artifacts on evalu
arXiv:2607.17122v1 Announce Type: new Abstract: Scope 3 greenhouse gas (GHG) emissions account for the majority of corporate carbon footprints, yet remain difficult to analyze at scale due to sparse disclosures, heterogeneous report document formats, and limited evidence traceability. Existing approaches typically rely on large language models to extract emissions information from ESG reports, but often lack explicit evidence grounding or depend on costly manual annotation and verification to ensure extraction reliability. To address these challenges, we propose Scope3Trace, an evidence-grounded information extraction framework designed to extract interpretable and traceable Scope 3 emissions information from real-world ESG and sustainability reports. The framework integrates a document information extraction pipeline that performs PDF collection and OCR parsing, LLM-assisted page localization and table reconstruction, and hybrid rule-LLM extraction of organization- and building-level
arXiv:2607.17111v1 Announce Type: new Abstract: We present the Bangladesh Legal Acts Dataset (BLAD), a curated collection of 1{,}484 legislative acts enacted between 1799 and 2025. Each act is represented with its full text, structured sections and footnotes, repeal status, and metadata linking it to the governing regime, head of state, and prevailing legal framework at the time of enactment. The corpus spans English, Bengali, and mixed-language documents, supporting temporal and multilingual analysis of statutory law. BLAD addresses a persistent gap in legal natural language processing (NLP) resources for low-resource, civil-law jurisdictions in South Asia. We describe the acquisition and enrichment pipeline, report descriptive statistics over more than two centuries of legislation, and outline the research directions the corpus enables. The dataset is publicly available under the CC~BY-SA~4.0 license at https://www.kaggle.com/datasets/sakhadib/bangladesh-legal-acts-dataset.
arXiv:2607.17043v1 Announce Type: new Abstract: Model collapse is a central challenge in learning from synthetic data: as later-generation large language models (LLMs) are trained on an increasing proportion of model-generated data, performance can degrade due to narrowed coverage and accumulated bias. Existing work mainly studies how to bound this degradation. In iterative model evolution, however, the more meaningful objective is to ensure that each successive model improves over its predecessor, which requires diagnosing collapse at a granularity that is actionable for data curation. We study this problem in synthetic data self-improving for instruction tuning. We show that collapse in this setting is not simply uniform performance degradation, but can appear as a polarization of competence, where synthetic training reinforces already strong skills while further degrading weak ones. Motivated by this observation, we propose KITE (Knowledge-boundary Instruction Tuning via Exploration
arXiv:2607.16872v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. However, reasoning-oriented post-training for dLLMs remains challenging. Supervised fine-tuning (SFT) for dLLMs requires dense but often off-policy masked states, while reinforcement learning (RL) relies on sparse rewards or value modeling. This paper proposes \textbf{trace-based on-policy distillation (TOPD)}, a teacher-supervised framework that transfers reasoning ability to a target dLLM without reward estimation. The key idea is to supervise a dLLM on its own denoising trajectory, focusing on the trace-aligned token decisions that form the final response. Specifically, TOPD samples on-policy diffusion trajectories from the target dLLM, obtains teacher token distributions from a teacher model on the corresponding partially denoised states, and updates the target dLLM with a token-level Reverse Kullback-Leibler (Reverse-KL) objective. This
arXiv:2607.16850v1 Announce Type: new Abstract: Entropy control has become an effective tool in reinforcement learning (RL) of large language models (LLMs), helping balance exploration-exploitation trade-off during alignment process. Such RL paradigm is often conducted on mixtures of heterogeneous tasks, which induce distinct entropy regimes under the same policy, making global or token-level entropy regulation insufficient to corresponding heterogeneous needs of exploration. This heterogeneity further makes GRPO-style normalized advantages induce an entropy-dependent bias, making advantage signals across prompt groups statistically non-comparable. To address this issue, we propose Group Entropy-Controlled Policy Optimization (GEPO), a lightweight extension to GRPO that uses group entropy, estimated from existing grouped samples to perform entropy-conditioned asymmetric advantage shaping. GEPO attenuates positive advantages in low-entropy groups to reduce over-exploitation, and negativ
arXiv:2607.16808v1 Announce Type: new Abstract: Event Argument Extraction (EAE) converts documents into structured event records by identifying argument spans and assigning them schema-defined roles. Document-level EAE is challenging due to long-range dependencies between triggers and arguments, cross-sentence context, and strict role constraints, which often lead to boundary errors, uncertainty in roles, and inconsistencies with restricted schemas. In this paper, we study whether mid-sized open LLMs can perform schema-constrained EAE reliably at the document level on MAVEN-ARG. Our approach combines (i) role-set injection in prompts for schema compliance, (ii) parameter-efficient supervised fine-tuning (LoRA) using the same JSON-only interface used at inference, and (iii) deterministic decoding with post-processing that validates JSON, filters invalid roles, de-duplicates arguments, and aligns spans to the document window. Under the official MAVEN-ARG evaluator, fine-tuned mid-sized o
arXiv:2607.16799v1 Announce Type: new Abstract: Hidden-state readouts can predict whether language-model outputs are correct, but objective correctness (OC) usually agrees with the model's own self-judgement (SJ), leaving the decoded signal semantically ambiguous. We construct conflict cases in which OC and SJ predict opposite readout orderings. On high-confidence disagreements, conventional correctness-labelled contrasts often rank incorrect/self-endorsed responses above correct/self-rejected responses, following SJ rather than OC. We estimate factorial SJ- and OC-associated directions and evaluate their polarity across mathematical reasoning and factual recall. Across four instruction-tuned models up to 14B parameters, the SJ-associated direction transfers above chance in both cross-domain directions for every model, whereas the OC-associated direction has a below-chance point estimate for the expected OC ordering in every corresponding condition. This transfer asymmetry develops acr
arXiv:2607.16790v1 Announce Type: new Abstract: Fine-grained offensive language detection organizes labels into a hierarchical structure, for which two modeling paradigms exist: cascaded decomposition and joint multi-task modeling. Prior work rarely provides a direct, controlled comparison of the two paradigms in terms of accuracy, parameter count, and inference latency, and rarely verifies whether a chosen class-imbalance handling strategy is actually optimal. This paper proposes a three-level cascaded detection system whose training strategy is customized per subtask, together with two verification mechanisms. First, a controlled ablation study determines the best class-imbalance handling strategy for each subtask. Second, a joint multi-task model with a shared encoder is trained as an architectural control, yielding real measurements along the dimensions of accuracy, parameter count, and inference latency. Experiments show that the cascaded system attains macro-F1 scores of 0.795, 0
arXiv:2607.16777v1 Announce Type: new Abstract: We present JOR-Bench, a collection of five Japanese-language benchmarks for evaluating the ability of large language models (LLMs) to formulate and solve operations research (OR) problems. Each benchmark is a Japanese translation of an existing English benchmark: IndustryOR, MAMO Complex LP, NL4OPT, OptiBench, and OptMATH, covering 1,319 problems spanning linear programming, mixed-integer programming, non-linear programming, and combinatorial optimization. JOR-Bench is a solver-independent benchmark that can be used with any solver or programming language, and consists of pairs of Japanese problem statements and expected numerical answers. We evaluate seven LLMs, including multilingual general-purpose models and Japanese-specialized models, on both the original English and the new Japanese versions, and compare performance across languages. For the main evaluation, we standardize execution with the Python interface to OR-Tools to make mod