Papers

AI agents are evolving from answer engines into persistent teams that use tools, delegate work, learn from experience, and modify the artifacts that shape their future behavior. The defining question for deployment is no longer merely what agents can do, but who controls what they are allowed to become. We introduce logos, a pluggable layer for self-evolution and governance that strengthens existing multiagent frameworks rather than replacing them. logos compiles heterogeneous multimodal inputs, including documents, images, audio, tables, databases, APIs, and human instructions into versioned agent packs containing agents, tools, knowledge, tests, permissions, and policies. During operation, it transforms agent activity into portable, auditable event traces and applies fail-closed verification across frameworks and backends. Every learned prompt, memory, skill, tool, role, or workflow remains an untrusted release candidate until held-out execution evidence, human-controlled policy, and explicit authorization permit its promotion. This architecture enables "verifiable human-agent loop engineering": agents can act, ask, learn, and propose improvements, while humans can steer objectives, permissions, approvals, and irreversible actions without interrupting continuous operation. logos provides a living logic for accountable automation. Agents may evolve at machine speed, but only evidence and human authority can close the loop.

Frontier language models are increasingly evaluated on biomedical benchmarks, but two problems undermine most published evaluations: legacy benchmarks are near-saturated, and open-ended responses are graded by other language models. We evaluate Claude Fable 5, Anthropic's most capable publicly available model, across eight biomedical benchmarks, four text and four multimodal, using deterministic scoring against fixed answer keys throughout. We include two Claude predecessors and GPT-5 as baselines. Refusal is tracked as a distinct outcome in every result table. That decision produces the paper's central finding. Fable 5 refuses between 8.0% and 99.4% of questions depending on the benchmark, a pattern absent in both predecessors and in GPT-5. Once refused items are excluded from the denominator, Fable 5's accuracy exceeds or meets every other model on every benchmark in this study. We identify two distinguishable refusal patterns: one concentrating in basic-science and mechanism content across MedQA and MedXpertQA MM, confirmed independently on two benchmarks using each benchmark's own category labels; and a separate disease-domain pattern on RareBench, where inborn metabolic disease presentations are refused near-universally while adult-onset autoimmune presentations are not. The primary constraint on Fable 5's biomedical usefulness is willingness to engage, not capability once it does.

Computational social science increasingly relies on automated preprocessing pipelines – speaker diarization, ASR transcript cleaning, sentence segmentation – to convert raw media into analyzable text. When these pipelines produce different outputs from the same input, two distinct sources of instability can arise: the preprocessing pipeline itself (diarization method, segmentation rules) and the downstream measurement instrument (LLM annotation vs.\ keyword lexicon). Using 256 YouTube interviews across 41 public figures from five domains, we compare two speaker-diarization pipelines and two measurement methods, all targeting the coupling between affective valence and epistemic modality. We find that (1) preprocessing pipeline sensitivity is concentrated in speakers with limited video samples (N $\leq 5$); for the four best-sampled speakers (N $\geq 16$), the mean absolute pipeline-induced change in $r(\text{neg}, \text{emph})$ is only $0.13$; (2) cross-method disagreement is larger and more systematic – the LLM and keyword-lexicon methods assign opposite coupling directions to several well-sampled speakers, even within the same preprocessing pipeline; and (3) aggregate valence proportions are highly stable ($|\Delta p(\text{neg})| < 6$pp) regardless of pipeline or method, masking both sources of instability. The contribution is a diagnostic framework that separates pipeline effects from measurement effects: researchers studying cross-dimensional relationships in interview data should verify that their conclusions are robust to both sources of variation, with particular attention to measurement method choice.

Multi-agent ensembling multiplies active parameters and inference cost without answering three basic questions: which agents to consult, how deeply a query should traverse a hierarchy of agents, and when inter-agent communication is worth its cost. We present GRADE (Gated Routing and Adaptive Depth for Efficient Reasoning), a hierarchical multi-agent system in which four lightweight learned gates jointly govern agent selection, hierarchy depth, inter-agent communication, and branch pruning. Training uses CoGRPO (Collaborative Group-Relative Policy Optimization), a novel critic-free recipe that adapts GRPO to multi-agent hierarchies and assigns a shared advantage signal to every gate and agent that participated in a rollout. Agent models are drawn from a hot-swappable Expert Registry; per-agent calibration maps allow experts to be replaced at inference time without retraining. At $\sim$17B average active parameters, GRADE outperforms all baselines on GSM8K, MMLUPro, and GPQA, surpassing the strongest baseline by 4.8 points on MMLUPro at half the active compute. On AIME-2025, where model depth dominates, GRADE remains competitive to existing frameworks. Ablations isolate the hierarchy and masked cross-attention as the largest contributors to accuracy, and show that per-agent calibration is necessary for safe hot-swapping.

Opinionated text - spanning product reviews, hotel feedback, and social posts - captures rich signals about user experiences, preferences, and concerns. However, the scale, redundancy, and imbalance of such corpora make it challenging to analyze opinions effectively, particularly when the goal is to generate summaries that remain faithful to the diversity of viewpoints expressed. This paper presents a framework that preserves semantics in LLM-based opinion summarization while minimizing token usage. We combine multidimensional classification (e.g., sentiment, topics) with a family of stratified sampling strategies to select compact yet representative subsets of opinions before prompting the LLM. Tailored prompts then produce balanced summaries that surface the salient aspects expressed in the opinions (e.g., strengths and weaknesses of products/hotels). Experiments on Amazon product reviews, Tripadvisor hotel reviews, and X/Twitter posts demonstrate that our method significantly reduces token usage and computational cost while consistently outperforming traditional AI-based and standard LLM summarization baselines in terms of content coverage, balance, and semantic preservation.

Quantifying abstractiveness in generated summaries is essential for evaluating summarization models beyond surface-level metrics like ROUGE. We introduce Reference Abstraction (RA), Summary Abstraction (SA), and Abstraction Ratio (AR) – a set of principled heuristic metrics that measure how much a summary diverges from extractive copying of the source text. The formulation uses the harmonic mean of document lengths modulated by a cubic non-overlap factor, yielding dimensionally consistent, bounded output with non-linear sensitivity to the extractive-abstractive boundary. Evaluation on 100 XSUM documents across four summarization models (BART-large-cnn, Pegasus-xsum, DistilBart, MT5-small) demonstrates that the metrics successfully discriminate between extractive models (SA ~ 0.12-0.26) and abstractive models (SA ~ 0.96-1.77), and that the Abstraction Ratio identifies summaries requiring manual evaluation for potential hallucination. Code and results are available at https://github.com/katweNLP/AbstractionStudy.

On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs). However, in complex reasoning tasks, OPSD paradoxically degrades downstream performance. In this paper, we systematically investigate this pathology and identify a severe optimization trap we define as Thinking Collapse – a sharp decline in the model's native intermediate reasoning behavior, measured by epistemic-token density (ET per 1k). Through entropy-based gradient masking and token-level target analysis, we show that this collapse is triggered by aggressive teacher gradients at high-student-entropy decision forks, where student epistemic tokens are frequently suppressed into teacher non-epistemic targets and are highly concentrated in high pointwise student-teacher divergence regions. To resolve this optimization pathology, we propose Adaptive Dual-Perspective OPSD (AD-OPSD), a robust control framework that dynamically moderates the self-distillation objective. AD-OPSD selectively anchors high-suppression-risk sandboxed tokens to a reference prior derived from the frozen base model via an asymmetrical pointwise divergence gate, preserving native thinking capacity while retaining OPSD's error-correcting power. Extensive experiments across competitive mathematical benchmarks show that AD-OPSD improves over standard OPSD by up to +4.1% absolute average accuracy across diverse model scales and datasets. Further analysis demonstrates that AD-OPSD mitigates thinking collapse and generalizes robustly to different post-training paradigms.

Multimodal retrieval-augmented generation (RAG) is often evaluated with clean evidence, yet real retrieval can return topically relevant but unreliable content: false text and misleading images from corrupted metadata, entity swaps, typographic overlays, semantic edits, adversarial patches, blends, or style transfer. We introduce QIMG-7, a controlled benchmark for multimodal retrieval pollution in multi-sentence factual QA, spanning four datasets, seven image-attack families, and 16 paired clean/polluted regimes, for 1,760 evaluation rows per method. Across four generator/gate stacks, naive multimodal fusion is brittle: in the main gpt-4o-mini stack, Full-MM support drops from 0.908 with clean text to 0.490 with polluted text, often making Parametric fallback safer than retrieval. We propose source-aware trust resolution (SATR), a training-free approach that compares Parametric, Text-only, and Full-MM candidate answers and selects among candidate answers or falls back based on source reliability. The Field-Selector variant achieves the best balanced score, 0.816, improving over Full-MM by 11.7 points and over the Cascaded Router by 2.7 points. Ablations show that, in this text-first setting, explicit text-reliability modeling is the dominant driver of these gains. Overall, in text-first factual QA with multimodal retrieval conflict, our results support selective trust rather than unconditional fusion. Artifacts are available at https://github.com/SaadElDine/Trust_Before_Fusion.

In open-domain multi-hop question answering (QA), LLM-based search agents offer a promising approach to knowledge-intensive QA by combining retrieval with reasoning. Existing methods mainly improve open-domain multi-hop QA through reasoning paradigms, retrieval interaction, and search strategy optimization. However, using multiple search trajectories introduces a challenging final answer selection problem. Different trajectories may support different candidates, and the retrieved information can be heterogeneous, redundant, incomplete, or conflicting. Directly comparing raw trajectories exposes the verifier to noisy and unaligned content, while comparing answer strings ignores the evidence supporting each candidate, making reliable final selection difficult. To address this challenge, we propose STEC, an evidence compression framework for final answer selection in multi-hop QA. STEC selects the final answer from the existing candidate set through two mechanisms: (1) Answer-Level Evidence Compression, which groups trajectories by normalized answer identity and converts each answer group into a candidate-specific evidence representation; and (2) Evidence-Guided Answer Verification, which compares these representations and selects the final answer from the candidate set. The design shifts final selection from raw trajectory comparison to candidate-level evidence comparison. We evaluate STEC on four open-domain multi-hop QA benchmarks against representative baselines. Experimental results show that STEC performs best overall among the compared methods, and ablation results provide evidence that answer-level evidence compression contributes to final answer selection.

The evolving realism of AI-generated Videos (AIGC-V) is rapidly rendering traditional artifact-centric detection insufficient, necessitating a paradigm shift from low-level inspection to high-level semantic verification. This paper presents a comprehensive survey of AIGC-V detection, reframing the task as Factual Fidelity Verification, which asks whether the events, entities, and physical processes depicted in a video are consistent with real-world facts. To systematize this rapidly evolving field, we propose a Vision-Language Dual-View taxonomy that organizes existing methods into a hierarchical, four-layer landscape, spanning intrinsic cue analysis, spatiotemporal consistency modeling, cross-modal consistency reasoning, and language-guided world-level reasoning. This dual-view framing highlights a fundamental transition from artifact matching in traditional deepfake detection to evidence-based semantic verification enabled by vision-language models and agentic reasoning pipelines. Based on a systematic review of 221 works, we synthesize AIGC-V generation paradigms, survey the landscape of detection methods, and review evaluation metrics and benchmarks in line with proposed views. Finally, we discuss current challenges and identify promising directions toward robust, explainable, and trustworthy detection.

This paper presents the first ChineseBabyLM Challenge, organized as part of NLPCC 2026. The challenge asked participants to train language models from scratch using no more than 102M Chinese words. The models were evaluated on three tracks: natural language understanding, cognitive alignment, and Hanzi knowledge. There were no restrictions on tokenizers, model architectures, or the number of training epochs. Eighteen teams submitted 28 distinct models, generating 74 result files. The overall-winning team used a DeBERTa-v2 architecture and introduced an auxiliary pinyin-prediction objective during pretraining. Several submissions also explored curriculum-learning strategies and architectural innovations. Overall, the challenge provides a benchmark for advancing data-efficient and cognitively plausible approaches to Chinese language modeling.

Recent advances in equipping Large Language Models (LLMs) with search tools and outcome-reward reinforcement learning (RL) have achieved new state-of-the-art results on open-domain QA tasks. However, we argue that current training paradigms harbor a critical vulnerability: they predominantly reward correct answers but fail to penalize fabricated ones when retrieval fails, thereby implicitly exacerbating hallucinations. To address this, we propose Abstention-Aware Reinforcement Learning (AWA-RL), which dynamically shapes the abstention reward utilizing the model's query-specific prior capabilities and continuous on-policy training observations. We also introduce a novel metric, RA-F1, to measure the capability-reliability trade-off. Compared to non-abstaining baselines, AWA-RL boosts absolute precision by up to 10.3% and overall RA-F1 by 2.9%, with only marginal sacrifice in raw accuracy. These results confirm that AWA-RL successfully yields highly capable and reliable search agents. The code, data, and model weights are publicly available at https://github.com/zfj1998/AWA-RL.

Persuasion techniques are powerful rhetorical devices used to sway public opinion in a wide range of media. We present a new corpus of persuasion techniques, focusing on Slavic languages. The corpus contains documents in Bulgarian, Polish, and Russian, annotated with persuasion techniques at the coarse-grained text-span level and fine-grained sentence level. The techniques are drawn from a taxonomy of 25 fine-grained persuasion techniques, grouped under six broad categories of rhetorical persuasion strategies. The corpus contains approximately 7500 text spans from 222 documents that cover topics hotly debated at the national and international levels. We describe the corpus creation process, provide detailed statistics, and examine correlations between topics and persuasion techniques. We use classic ML-based and generative AI-based models to provide baselines and benchmark results for the detection and classification of persuasion techniques at the text-span level and sentence level.

Self-attention is a ubiquitous primitive in modern sequence models, yet its operator-level geometry is only partially understood. We view a token sequence as a vector field over the token-position graph and identify attention as a connection walk: messages are aggregated by a nonnegative walk matrix while being transported along each edge by a learned linear map. Within this framework, we prove that single-head attention (SHA) is exactly a connection propagation step with constant transport, and that multi-head attention (MHA) is exactly a single edge-dependent connection walk whose effective transport is an attention-gated mixture of headwise transports. We further clarify the conditions under which the corresponding generator reduces to a random-walk connection Laplacian, highlighting the roles of stochasticity, reversibility, and metric-compatible transports. Empirically, we find that trained Transformers across scales (from 124M to 8B) and structures (encoder/decoder) exhibit geometric structure consistent with our theory: effective attention graphs converge to stable geometric operators in deeper layers, learned transports self-organize into approximate scaled isometries, and both phenomena strengthen consistently with scale. Overall, the paper provides a precise connection-walk formalism that links self-attention to classical geometric operators, along with a set of operator-level tools for analyzing transformer models from a geometric perspective.

Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks. However, traditional speculative decoding typically relies on auxiliary draft modules, incurring significant training and communication overhead. Although recent methods attempt to generate drafts within the target model itself, they often fail to fully exploit its latent parallel capacity due to a lack of structural coordination. In this paper, we propose Progressive Tree Drafting (PTD), which employs a structured, guided parallel drafting strategy to harness the model's parallel potential. By coupling a progressive tree structure with a stepwise pruning mechanism, PTD actively guides the LLM to explore multiple semantic paths in a single forward pass, ensuring both draft diversity and coherence. Experiments demonstrate that PTD achieves up to $2\times$ decoding speedup across various benchmarks while remaining training-free and model-agnostic. Our code is available at: https://github.com/MINE-USTC/PTD.

The rapid integration of Large Language Models (LLMs) into K-12 and higher education has outpaced the development of reliable methods for evaluating their pedagogical quality. As the research community starts to explore the space of automating evaluation of AI tutors, we introduce FATE (FLC AI Tutor Evaluator), a specialized 8B-parameter language model designed to evaluate AI tutors. Aligned with the four core evaluation tracks from the BEA 2025 Shared Task, our model assesses pedagogical ability across Mistake Identification, Mistake Location, Guidance, and Actionability. Because pedagogical evaluation is a specialized task with limited labeled data, we leverage knowledge distillation from a frontier LLM to generate additional supervision, yielding absolute performance gains up to 22.63 percentage points. Finally, we demonstrate FATE's utility as an automated evaluator by benchmarking instructional responses generated by popular commercial models, including ChatGPT, Claude, Gemini, and DeepSeek. On average, we have found that Gemini 2.5 Flash perfomed best (82.88%), then ChatGPT 5.5 Instant (80.75%), followed by DeepSeek V4 Flash (80.13%) and Claude Sonnet 4.6 (74.00%).

An LLM agent's public behaviour reveals little about its social reasoning: an agent that votes correctly may be guessing, and an agent that lies well leaves no trace of what it actually believes. We present MafiaScope, an open testbed that turns the social deduction game Mafia into a measurement instrument for machine Theory of Mind. It distinguishes whether an agent lost because it misread the game or because it failed to act on a correct assessment, a distinction that is invisible from outcomes and dialogue transcripts alone. After every public utterance, each agent privately answers structured probe questions whose responses never re-enter the game and are scored against the ground truth known to the engine. An interactive visualizer replays games from the perspective of an individual agent's beliefs, displays timeline-aligned accuracy and calibration, and supports counterfactual replay from any recorded step. In a case study across two model families comprising tens of thousands of parsed probe responses, we find that stated confidence is poorly calibrated, agents overestimate how often they are suspected by a factor of 1.5, and single-vote counterfactual replays rarely change game outcomes: outcome flips occur primarily when the agent had already formed a correct belief state, whereas decisions made under an incorrect model of the world remain largely unchanged under resampling. The engine, visualizer, recorded games, and counterfactual replay corpus are released under an open-source licence. Code: https://github.com/karpovilia/mafiascope. Live demo: https://karpovilia.github.io/mafiascope/. Screencast: https://vimeo.com/1208920221.

We present Anamnesis, an interactive system for demographically controllable survey simulation using large language models. Open-source and designed for non-technical users/researchers, Anamnesis enables the prototyping and stress-testing of survey instruments on virtual populations rather than real human subjects. The platform operationalizes the recently introduced Anthology and Alterity frameworks, which use structured narrative backstories to condition model responses, within a unified web interface. It supports open-ended generation, probabilistic demographic resampling, and multimodal (image and audio) surveys. We evaluate the system through two case studies: (1) replicating segments of Pew Research Center's American Trends Panel (ATP) on political typology and biomedical issues and (2) emulating human preference in the New Yorker Caption Contest. In both cases, Anamnesis produces opinion distributions that more closely match real-world survey data than standard persona-prompting baselines, offering a transparent, reproducible, and open-source alternative to proprietary simulation services.

LLM-as-a-judge evaluation is widely used for retrieval-augmented generation (RAG), but reusing the same model family as both generator and judge makes self-leniency difficult to identify. We introduce Eval-Pair Matrix, a controlled meta evaluation protocol for source-grounded RAG. Starting from GaRAGe questions and grounding passages, we induce one hidden answer-causal contradiction per record, generate answers from perturbed passages with GPT, Grok, and Gemini models, and then use the same models as blind judges to evaluate each answer against the original passages. The experiment contains 300 core records, 897 labeled generator outputs, and 2,683 judge verdicts in a crossed 3 x 3 matrix; the primary analysis uses 275 fully validated records. Instead of comparing diagonal and off-diagonal cells across different answers, we estimate same-model effects by pairing judges on the exact same candidate answer. This changes the interpretation: diagonal and off diagonal F1 are similar, and the paired same-model recall effect is near zero (-0.5 pp; 95% cluster bootstrap CI [-2.7, +1.7]). The only robust paired gap is lower matching-judge flagging for answers that avoided the induced claim (-4.3 pp). A targeted human evaluation finds that reviewed apparent false positives are alternate source-error detections, mistakes in labeling whether the induced claim was adopted, or unclear cases; none were adjudicated as genuine false alarms. The lesson is methodological: RAG judge studies should report full matrices, answer-paired effects, behavior strata, and label-task alignment.

Non-binary bottom-up constituency parsing commonly uses arity-specific reductions such as \(\textsc{Reduce-}X\#k\), which jointly specify the mother label and number of children. We show that arity need not be a primitive transition parameter. The proposed parser predicts the mother label separately and identifies the ordered child sequence from a delimiter-bounded stack configuration. In every well-formed reducible configuration, the active delimiter, label marker, and intervening completed items uniquely determine the reduction domain and hence its arity. This factorization removes label–arity-specific reduction actions while preserving direct construction of the original non-binary trees. Controlled experiments on PTB and CTB show that the delimiter-guided parser closely tracks an arity-specific baseline while using a substantially smaller action inventory. Its predicted trees retain the gold branching profile without systematic collapse at higher arities. The smaller inventory is obtained at the cost of longer derivations and boundary-sensitive errors involving delimiter insertion, preservation, and consumption.

We investigate how annotator demographic attributes, supplied as prompt cues, shape the alignment between large language model (LLM) predictions and human annotations across five tasks. Using five open-source LLMs, we systematically vary the number and composition of demographic components in the prompt, spanning every combination from single-attribute through full-attribute configurations. Our experiments reveal three principal findings. First, alignment consistently peaks with one to three high-signal attributes and degrades under the full attribute set, establishing a clear over-specification threshold. Second, the overall magnitude of demographic influence on human annotations does not predict which attributes improve LLM alignment; instead, both the learnability and the directional coherence of each attribute's annotation signal need to be considered jointly. Third, neuron probing reveals that specialized activation correlates with alignment gains only under coherent annotation signals, and that activation volume alone does not imply steerability. Together, these results demonstrate that demographic prompting is not a monolithic intervention: its utility is highly context-dependent, shaped by attribute signal quality, task characteristics, and model architecture.

Tasks such as customs tariff classification, export control categorization, and standards-based equipment coding require assigning an input instance to a fine-grained class under an explicit regulatory hierarchy. Unlike standard text classification, the correct label in these tasks is not determined by semantic similarity alone, but by rule-defined boundaries, threshold conditions, exclusion clauses, definitions, and local exceptions. As a result, two highly similar inputs may require different labels, while a retrieved passage that appears relevant may still be inapplicable under the governing rules. Existing flat classifiers, hierarchical text classification methods, and retrieval-augmented LLM systems are not designed to jointly enforce hierarchical validity, rule consistency, and fine-grained boundary reasoning. In this paper, we formulate this setting as regulation-driven fine-grained hierarchical classification, where an external instance must be assigned to a fine-grained class through a valid path in a regulatory hierarchy and supported by auditable evidence. We construct four benchmark datasets from representative regulation-intensive scenarios and validate the annotations through an expert-in-the-loop process. We further propose a constraint-aware hierarchical search framework that converts regulatory documents into a searchable tree, retrieves only valid local candidate nodes, and uses structured regulatory fields with evidence snippets to guide each next-hop decision. Experiments show that our method achieves the best mean accuracy on all four datasets and provides interpretable decision paths, with the largest gains on cases involving fine-grained neighboring categories and rule-based boundary conditions.

Multimodal BrowseComp tasks require agents to combine perception, tool use, and long-horizon reasoning over dynamic web content, challenging their ability to handle compositional structure, open-world uncertainty, and multimodal integration across extended interactions. Crucially, real-world multimodal browsing involves three distinct information-flow patterns: text-only, image-to-text, and text-to-image, yet existing data construction methods cover only the text-only and image-to-text patterns, leaving text-to-image largely unaddressed and limiting agent generality and robustness. We introduce UNIBROWSE, a unified data pipeline that for the first time simultaneously generates training data covering all three patterns, augments curated knowledge graphs with live web retrieval for improved fidelity, and introduces a novel metric of exploration degree to filter low-signal instances for efficient reinforcement learning. Through this pipeline, we produce high-quality cold-start tool-use trajectories and exploration-rich QA pairs, and train a 35B-scale agent via supervised fine-tuning and exploration-aware RL.The resulting UNIBROWSE agent achieves state-of-the-art performance on multimodal BrowseComp benchmarks, attaining an average accuracy of 54.4 across five diverse benchmarks – an improvement of 10.5 points over its base model Qwen3.5-35B-A3B – and surpassing serveral closed-source agent workflows such as GPT-5 (42.9), Gemini-2.5 Pro (44.8), and Gemini-2.5 Flash (41.3).

Generative Large Language Models (LLMs) have revolutionized information retrieval, yet their strictly parametric nature frequently leads to severe factual hallucinations when confronted with complex queries beyond their epistemic boundaries. While external tool-calling can mitigate this, indiscriminately invoking search tools for every document during reranking incurs prohibitive latency overheads, creating an intractable accuracy-efficiency dilemma. To address this challenge, we propose TALRanker, a novel framework that formalizes pointwise relevance scoring as an agentic Markov decision process. We optimize it via a two-stage training paradigm. An initial warm-up utilizes a language-preserving hybrid loss to prevent the catastrophic forgetting of native generative capacities. Subsequently, an asymmetric cost-aware reward equipped in reinforcement learning forces the policy to autonomously bypass tools for maximum efficiency when confident, while selectively retrieving external evidence to avert severe hallucination penalties when uncertain. Extensive evaluations demonstrate that TALRanker achieves state-of-the-art performance across standard and reasoning-intensive retrieval benchmarks, matching throughput with pointwise rerankers while outperforming parameter-heavy reasoning models.

When an LLM judge calls a peer review analytical and a human committee calls another review high quality, are they tracking the same thing? We argue they are not, and that the difference matters philosophically. We operationalise Kahneman's dual-process theory into a structured rubric for peer review and release Kahneman4Review, a benchmark of 3,563 rated reviews scored along nine theoretically motivated textual dimensions, eight bias diagnostics, and a continuous reasoning-quality score. Three findings bear on trustworthiness: decision tier is not detectably aligned with the rubric's text-grounded epistemic-quality proxy; public-showcase agentic reviews receive higher raw scores than pooled human reviews, but length and venue explain most of the gap and the samples are not paper-paired; and ICLR review-text diagnostics shift at the 2022–2023 transition, temporally coincident with widespread LLM availability but without identifying its cause. A matched function-probe pilot further shows that the rubric distinguishes textual probes designed to contrast genuine fault-finding with surface fluency. We argue that a trustworthy reliability benchmark for LLM judges must separate analytical form from epistemic function, and propose concrete design choices toward that goal. An interactive demo is available at https://huggingface.co/spaces/nuojohnchen/Kahneman4Review.

Language generation research increasingly spans three paradigms: autoregressive decoding, discrete masked diffusion, and continuous flow-matching. Comparing them is difficult because each lives in a separate codebase, so measured differences often reflect implementation details rather than the paradigms themselves. We present DantinoX, an open-source JAX/Flax library in which a single modular Transformer backbone serves all three paradigms. Switching the generation paradigm, attention mechanism, or hardware topology requires only a configuration change, while the backbone architecture, tokenizer, initialization strategy, and training infrastructure remain consistent. This enables controlled cross-paradigm comparisons within one API for training, streaming inference, and benchmarking.

Large language models (LLMs) are increasingly integrated into financial advisory systems, yet their role in reproducing religious bias remains underexamined. This study provides systematic mixed-methods evidence of such bias across three LLMs (ChatGPT, Gemini, and Grok) using 432 simulated advisor-client interactions spanning 16 religious identity pairings (Christian, Muslim, Hindu, and non-religious) and three core household financial decisions: stock investment, house purchase, and life insurance. Combining regression and reflexive thematic analyses, we identify structural biases across models and decision contexts and the discursive mechanisms through which they are linguistically enacted. Unbiased advice appeared in only 12-18% of cases. Gemini consistently produced more bias than Grok, while ChatGPT's outputs were statistically comparable to Grok's. Religiously symmetric advisor-client pairings almost always triggered explicit religious framing, and non-religious clients often received advisor-centered religious appeals. Qualitative findings show that bias is linguistically manifested through religious anchoring, uneven cultural signaling, and tone modulation, varying by model and financial scenario. Stock investment prompts produced more financially technical responses, whereas life insurance advice triggered stronger religious language. The study develops a dual-dimensional framework linking structural bias rooted in model training and design with discursive bias expressed through language, advancing understanding of algorithmic bias in LLM-generated financial advice. It also shows that such advice adapts linguistically to identity cues, revealing a managerial dilemma between personalization and neutrality. Finally, it highlights implications for businesses, financial institutions, and regulators seeking to ensure neutrality, cultural sensitivity, and trust in AI-mediated advice.

A recurring proposal in legal AI is to improve case-outcome prediction by fusing uncertainty tools (evidence graphs with belief propagation, sequential Bayesian odds updating, Dempster-Shafer combination, and conformal prediction) into one pipeline. We test this on 1,000 real European Court of Human Rights cases from LexGLUE and FairLex, predicting whether the Court found a Convention violation from the case's fact paragraphs. We compare three families across two frontier LLMs (Claude Opus 4.8 and GPT-5.5) as per-fact evidence estimators: (A) the raw LLM, (B) the LLM routed through the fusion pipeline, and (C) a term-frequency baseline through the same pipeline. Across roughly 4,750 tests we find: (1) on discrimination (AUROC around 0.83) the pipeline yields no improvement over either the raw LLM or the baseline; a frontier LLM used directly is the strongest single discriminator. (2) Naively composing an LLM with Bayesian-odds and Dempster-Shafer fusion more than doubles calibration error (ECE from about 0.16 to 0.46) via a prior-mismatch mechanism that replicates across both models. (3) Dempster-Shafer fusion is actively unsafe on long chains, committing confidently to wrong labels at below-chance accuracy; we recommend removing it. (4) The pipeline's genuine value is operational: routed through a conformal selective-prediction layer, the system decides which cases to automate and which to escalate. After removing Dempster-Shafer, recalibrating, and applying class-conditional risk control on the full 1,000-case set, the tuned engine auto-clears at 96.8 percent accuracy with 0.5 percent errors escaping and 96.3 percent caught for review, versus 85.9 / 3.8 / 72.1 for an untuned baseline. The contribution of such pipelines in law is calibrated trust, not sharper prediction.

Large language models produce chain-of-thought (CoT) reasoning that appears logically sound yet may not genuinely depend on its stated premises. We introduce interventional grounding audits, a black-box, step-level test of premise dependency: we intervene on a single premise by substituting its target predicate with a fresh symbol, re-run the model, and check whether each reasoning step's normalized conclusion (canonical predicate form) changes. We evaluate on ProntoQA, a synthetic multi-hop deductive reasoning benchmark with gold proof trees, where step-level premise dependencies are known. Applied to 50 ProntoQA problems with GPT-4o, our method achieves F1 = 0.806 on detecting proof-tree dependencies (F1 = 0.885 on predicate-determining dependencies; Recall = 100%), significantly outperforming a self-consistency baseline (F1 = 0.343; 95% bootstrap CIs non-overlapping). We further identify that 66% of correctly-solved problems contain at least one aligned step insensitive to a direct proof-tree dependency under consistent substitution – all involving entity-introduction premises, a documented blind spot of the consistent-substitution evaluator – a "right answer, wrong reasoning" signal invisible to passive methods. All audit certificates, raw outputs, and reproduction scripts are available in a public GitHub repository, and we discuss scope limits beyond formal, parsable benchmarks.

Large language models can write SQL, but enterprise deployment demands more than plausible text: outputs must be syntactically valid, must respect per-role and per-schema policy, must carry provable (not best-effort) guarantees, must not slow down as generations grow, and must leave a compliance-grade record of every decision. We present GRID (Grammar-Railed Decoding), a grammar-constrained decoding engine that keys exact next-token masks on parser configurations (lexer scan state x LALR(1) stack) rather than on token sequences, and uses the incrementally advanced LALR(1) parser itself as a viable-prefix oracle. LLM tokens are bridged to grammar terminals by a byte-level trie walk with a context-independent/context-dependent split that makes cache-key soundness hold by construction. Role-based access control is compiled into the language: role projections subset the grammar's productions and schema lexicons restrict identifier terminals, so forbidden verbs and identifiers are unreachable at mask level. Four guarantees (soundness, completeness, termination, and near-constant per-token cost) are stated with explicit preconditions and each paired with a test or benchmark. Rust kernels bring the per-token mask to a 3.6-6.7 us median, ahead of llguidance at p50 and p90 on two tokenizers with zero false rejects; per-token guard cost is position-flat at n=16,000. On Spider, constrained decoding is worth +13 execution-accuracy points at 0.5B, and one checker-guided repair pass over the provably mask-unenforceable residue (column-level policy) lifts a 7B model to 94.5% executable. A hash-chained per-token audit trail replays bit-identically with 100% tamper detection. We state plainly what the mask cannot do (distribution faithfulness, column-level RBAC, non-LALR(1) languages) and where measured cost remains.