Searcharxiv⌕ Search

subject

cs.CL

cs.CL: explore 1934 source-linked works published from 2017 to 2026, with original documents and citations.

This collection is a preview while coverage and quality are evaluated.

Search within this collection

Coverage and selection

Includes records with this source-supplied label or an explicit phrase match in their metadata. Matches indicate a mention, not proof that a paper uses a method or tests a material. Source versions are consolidated by DOI.

Sources: arxiv. Collection updated 2026-09-16. Counts describe this index, not the complete source archives.

arXiv2026

The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits

Whether a language model looks demographically biased can depend on how the audit asks its question. A charitable-aid benchmark reports that the same models favor minority applicants when rating requests one at a time and penalize some when ranking side by side. We test whether that reversal generalizes to hiring, lending, and medical triage: 40,726 requests to five models, applications differing only in the applicant's name, and a primary test fixed before collection. It does not. None of 36 planned contrasts survives correction. The rating advantage keeps its sign at roughly half the published size, and a precision extension bounds any hiring ranking penalty below the published effect, though the lending and triage ranking floors sit above that margin, so the exclusion is conclusive for hiring ranking and for rating in all three domains only. Planted disparities tracking their injected sizes and a directional replication on the original aid materials bound these nulls. The audit is livelier than the demographics: models recognize transparent audits nearly always, tie every identical-content comparison whether the varying detail is race or a hobby, and reward first-listed candidates as much as any demographic effect we measure. Audit verdicts reflect audit construction more than demographic bias.

cs.CL↗
arXiv2026

Performance of Clinical AI System and Physicians and Frontier Language Models in primary care diagnostics

Clinical AI evaluation should encompass diagnosis and management after adaptive information gathering. We compared Doctorina, eight physicians and four standalone frontier language models in 150 synthetic Polish-language primary-care consultations. Doctorina achieved 82.0% Top-1 concordance versus 57.0% for physicians (difference, 25.0 percentage points; 95% confidence interval, 17.7-32.7) and 97.3% versus 85.0% primary-or-reference-differential concordance. Across 149 case pairs, normalized workup and treatment scores were 89.4 versus 66.9 and 83.7 versus 61.2. Doctorina had the highest diagnostic point estimates among all six groups; Kimi K3 ranked next, while Claude Opus 5 led the closely spaced management estimates of Opus, Doctorina and Kimi. A second Doctorina execution reproduced the advantages over physicians across all outcomes. Doctorina's advantage over physicians therefore extended from primary-diagnosis selection to higher-rated diagnostic workup and initial treatment after adaptive consultation.

cs.CL↗
arXiv2026

ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback

High-quality tool-use data is critical for training language models to interact effectively with external tools. However, existing synthetic approaches typically follow a generate-then-filter paradigm with static post-hoc verification, often yielding inefficient data with imbalanced feature distributions. We propose ToolLoop, a closed-loop framework that decomposes synthesis into three progressive stages: (1) sampling function name combinations as ground truth; (2) backward derivation of user queries; and (3) forward derivation of tool calls. At each stage, dynamic self-feedback iteratively guides the model toward high-quality generation, realizing a transition from generate-then-filter to generate-verify-refine. On the Berkeley Function Calling Leaderboard (BFCL), a 4B parameter model trained with our 11K synthetic examples achieves 86.40% accuracy in non-reasoning mode, while an Isolate variant that removes BFCL-overlapping candidate functions still reaches 86.07\%. Cross-benchmark evaluation on ACEBench further demonstrates strong generalization, with 72.1% overall accuracy using only 18.3% of baseline training data.

cs.CL↗
arXiv2026

ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation

As LLMs are increasingly used for pre-submission self-review, there is growing demand for feedback that not only identifies weaknesses but also guides authors toward concrete revisions. We study this as Actionable Peer-review Generation and decompose it into two subtasks: diagnostic claim generation and revision suggestion generation. We introduce ActReview, a rebuttal-guided post-training framework that connects paper-specific diagnoses to concrete, grounded revision plans. Our central insight is that author rebuttals reveal plausible actions for addressing reviewer concerns and can therefore provide latent supervision for revision-oriented feedback. From real review-rebuttal threads on OpenReview, we construct ActReview-40K by aligning reviewer weaknesses with author responses and grounding the resulting feedback in localized paper evidence. We post-train Qwen3-8B-Base with multi-task supervised fine-tuning followed by GRPO using candidate-aware, weakness-specific rubric rewards. We also introduce ActReview-Bench, a human-curated benchmark of 1,000 instances for evaluating diagnostic quality and revision usefulness. Experiments show that ActReview outperforms prior specialized review-generation models on actionability and grounding while remaining competitive with strong prompt-based LLMs. Human evaluation confirms improved revision usefulness while revealing a remaining gap in technical accuracy, and additional analyses support generalization to held-out papers and robustness across independent judges.

cs.CL↗
arXiv2026

It's Not RoPE that Creates Sinks: The Role of Self-Concentration and Value-Non-Mixing in Attention

Large Language Models (LLMs) often exhibit "Attention Sink" (AS) and the accompanying "Massive Activations" (MAs) at the initial position of a sequence. These phenomena frequently co-occur, and MAs can pose challenges for low-bit quantization. In this study, we analyze the factors underlying AS and MAs that emerge at the initial position regardless of the token occupying it. Our experiments suggest that self-concentration of attention, resulting from the causal mask, and the subsequent Value-non-mixing in attention outputs contribute to AS and MAs. These findings provide new empirical evidence on the internal dynamics of LLMs, offering insights that may inform future quantization strategies and advance our understanding of the internal mechanisms of attention layers.

cs.CL↗
arXiv2026

SPINE: Measuring LLM Sycophancy under Sustained Multi-Turn Pressure

Large language models (LLMs) may abandon correct positions when users push back, exhibiting a failure mode known as sycophancy. Existing evaluations typically use short, prespecified conversations and may therefore miss failures that emerge under sustained, adaptive disagreement. We introduce SPINE, a benchmark in which an LLM proxy plays a persistent but mistaken user and adaptively challenges a target model for up to 25 turns. We evaluate four commercial models (Claude Sonnet 5, GPT-5.6 Terra, Gemini 3.1 Pro, and DeepSeek V4 Pro) and three Olmo3-7b models on 100 false presuppositions and 100 unethical queries. We define collapse as a target model abandoning the correct position and yielding to user pressure. Our experimental results show that collapse rates increase with conversation length across post-trained models, with the overall rate rising from 0%-57% within 5 turns to 20%-97% within 25 turns depending on model and scenario. These results show that evaluations limited to a few conversational turns underestimate sycophancy and resistance under sustained pressure remains unreliable across current models. By analyzing models with accessible reasoning traces, we surprisingly found that the correct position often remains represented in the trace in 50%-89% of analyzed collapse turns, suggesting that the model chooses to please a user and sycophancy is not due to ignorance or the correct knowledge being overridden. Ablations show that the SPINE protocol substantially increases the sycophantic collapse rate compared to pre-generated scripts. Among all tactics, emotional appeals are most associated with inducing LLM sycophantic behavior, with position weakening in 44.3% of turns using this tactic. Code, data, and transcripts will be released upon publication.

cs.CL↗
arXiv2026

ExecCritic: Learn to Test, Test to Improve for Coding Agents

Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agent-generated tests can encode incomplete or incorrect behavioral targets; when the same trajectory writes both the patch and the test, their errors can agree and create false confidence. We introduce ExecCritic, combining a test--verify--revise scaffold with a role-specific reinforcement learning recipe for training agents within it. The scaffold separates test construction from source-code repair: a Test agent independently generates repository-native tests, a fail-closed harness qualifies and freezes them, and a Repair agent revises source code from their execution feedback without changing the tests. Both roles use Qwen-3.5-35B-A3B as the backbone and are trained separately. In Learn to Test, the Test agent learns to produce behaviorally valid tests that distinguish correct from incorrect patches. In Test to Improve, the Repair agent learns both direct task resolution and feedback-guided revision. On SWE-bench Verified, test quality determines whether feedback helps: holding the base Repair agent fixed, tests from the base Test agent reduce resolved rate from a no-test baseline of 61.2% to 57.3%, whereas tests from GPT-5.6-sol raise it to 65.3%. Role-specific post-training raises the Qwen Test agent's Base-to-Gold success from 22.2% to 62.2%; composing the two post-trained Qwen agents reaches 72.6%, an 11.4-point gain over the original no-test baseline without stronger-model or Oracle feedback at evaluation time. Code is publicly available at https://github.com/MSR-Orchard/execcritic.

cs.AI↗
arXiv2026

Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation

Existing methods for test-time reinforcement learning (TTRL) derive rewards from answer-level self-voting on unlabeled test-time tasks with canonical answers, but this breaks down for code generation because programs cannot be compared by surface form and therefore do not directly provide a usable training signal. To make TTRL applicable to code generation, we propose probe-driven TTRL, which constructs output-free probe inputs from the problem statement, executes candidate programs on these probes, and defines a Probe Consensus Reward (PCR) from the resulting behavioral agreement. PCR provides a behavioral training signal for open-vocabulary programs, but it is not a fully reliable verifier and remains susceptible to reward hacking through spurious consensus. We therefore introduce Entropy-Regularized Rank-Masked Policy Optimization (ERPO), which converts low PCR into conservative negative updates through rank masking and controls policy drift with an entropy ceiling. On coding benchmarks, ERPO substantially improves pass@1 and pass@k in both in-domain adaptation and zero-shot transfer.

cs.LG↗
arXiv2026

A Data-Driven Framework for Identifying and Prioritizing RPA Opportunities in Healthcare Processes

Robotic Process Automation (RPA) is widely used to reduce administrative burden in United States hospitals, yet an estimated 30-50% of RPA initiatives underperform because processes are selected informally, without a repeatable method to catalogue candidates, prioritize them, match each to an automation tier -- a Python bot, an open-source orchestrator such as n8n, or an enterprise platform such as UiPath -- and forecast financial return before committing resources. We propose a four-module, data-driven framework unifying these decisions: a Process Taxonomy of twenty recurring hospital processes across five value streams; a Prioritization module deriving an Automation Suitability Index from an Analytic Hierarchy Process matrix with an explicit consistency check; a Tool-Tier Selection module recommending the least-cost technology sufficient for a process complexity, integration, and compliance profile; and a Return-on-Investment module quantifying labor savings, error-cost avoidance, payback, and net present value. Applied to a synthetic portfolio spanning all twenty processes, plus a reference data-flow architecture linking it to hospital EHR/payer/ERP systems: 12 of 20 clear the prioritization threshold; the ranking is robust to +/-20% weight perturbation (Spearman correlation 0.83, top-5 set preserved 97.7%, 2,000 Monte Carlo trials); an Automation Risk Index flags four qualifying processes as Critical risk; a budget-constrained portfolio optimization shows diminishing marginal NPV as spend scales from $400K to $1.03M; and a second Monte Carlo analysis shows portfolio NPV stays positive at its 5th percentile. The framework is a conceptual synthesis of the literature rather than an instrument calibrated on primary hospital data; we discuss HIPAA governance and a research agenda for empirical validation. A supplementary Python implementation accompanies the paper.

cs.AI↗
arXiv2026

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

Image tokenizers define the ``visual language'' of unified multimodal models, yet are commonly studied through isolated metrics or generation-/understanding-only evaluations. These evaluations do not fully capture how visual tokens behave when modeled jointly with text. We build a controlled pure-autoregressive testbed and track task-specific validation losses during multimodal continual pretraining across text, image, text-to-image (T2I), and image-to-text (I2T) prediction. We examine how these losses scale and relate to downstream performance, then use them to study multimodal learnability---how well image and text tokens are jointly modeled---and tokenizer design. We find that (1) losses should be analyzed by task, since they exhibit distinct scaling behavior and rank tokenizers differently. (2) The loss--performance relationship depends on the predicted token space: for a fixed tokenizer, T2I and I2T losses correlate with generation quality, but across tokenizers, the T2I loss--performance relationship shifts with the image-token space, whereas I2T loss, computed over a shared text vocabulary, provides a more consistent signal. I2T loss also correlates with both generation and visual understanding performance after supervised finetuning. Using losses as a lens, we show that (3) better reconstruction does not necessarily yield lower task-specific losses or stronger downstream performance, and that (4) image tokenizer choice can affect text modeling under joint optimization. As case studies, we revisit three tokenizer design axes---the discriminator, semantic supervision, and vocabulary size---to examine their effects on joint modeling and downstream performance. Together, our testbed offers a complementary perspective on image tokenizers as visual languages, highlighting their interplay with text in joint multimodal training.

cs.CV↗
arXiv2026

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. Most agents select actions through unconstrained generation over an accumulating history, leaving implicit the procedural knowledge of what to do, in what order, and under which conditions. As trajectories lengthen, agents can lose track of their objectives, invoke tools out of order, and repeat unproductive actions. We introduce the Procedural Graph: just as a knowledge graph organizes factual knowledge into (entity, relation, entity) triplets for what-is questions, a Procedural Graph organizes procedural knowledge into (procedure, relation, procedure) triplets for what-to-do questions. At each decision step, the framework localizes the agent's active node, and a guidance model translates the surrounding subgraph into step-level situational guidance that biases the solver's next action without dictating it. The graph is self-evolving: an LLM refiner contrasts failed trajectories with successful ones and edits the graph's topology and attributes, committing edits that preserve or improve held-out validation performance while retaining rejected ones to discourage repetition. Starting from a minimal skeleton, the loop builds graphs that match or surpass hand-designed ones. It can also repair a flawed expert prior. Across multiple datasets, task types, and LLMs, the Procedural Graph delivers consistent gains over memory-based baselines, and self-evolution further improves performance without manual engineering.

cs.AI↗
arXiv2026

ReCite: Agentic Reasoning for Faithful Citation

Accurate citations are the foundation of academic writing, tracing intellectual origins and substantiating core claims. However, manually navigating the growing volume of scientific literature is increasingly difficult, prompting reliance on automatic citation recommendation. While modern retrieval-augmented architectures have largely mitigated the fabrication of non-existent papers, current systems relying on semantic similarity struggle with misattribution, often citing authentic papers that fail to logically support the author's claim. To address this challenge, we argue that accurate citation requires a shift from similarity-based search to active, claim-level reasoning. We propose ReCite, a decoupled agentic framework that orchestrates location perception, intent-aware query planning, and reflective verification. Trained on synthesized reasoning trajectories, our agent verifies claim-evidence consistency and triggers self-correction loops when retrieved candidates lack logical support. Experiments demonstrate that our lightweight framework outperforms state-of-the-art massive generative models in strict citation accuracy. By grounding literature matching in verifiable logic rather than semantic overlap, ReCite establishes a reliable foundation for automated academic writing.

cs.CL↗
arXiv2026

Learning Length-Extrapolatable Recurrent Models

Recurrent models provide a natural path to long-context modeling, yet models trained with backpropagation through time (BPTT) often fail beyond their training horizon. Classical analyses emphasize gradients that vanish or explode along temporal paths. However, dense per-token losses can still train a shared recurrent rule despite severe decay, showing that decay alone does not determine whether learning fails. We instead study state credit: the signal through which future losses reach earlier recurrent states before contributing to parameter updates. Accordingly, we intervene directly on state credit and propose Credit Stabilization through Time (CST). During backward propagation, CST locally rescales the state-credit signal to stabilize its norm without rotating the component being corrected, while leaving the forward computation unchanged. Because controlled synthetic tasks and real data exhibit different credit dynamics, we specialize CST to each regime. In both settings, CST improves performance beyond the training horizon, with gains observed at up to 128x the training length.

cs.LG↗
arXiv2026

Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts

Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling model capacity while preserving efficient inference in large foundation models. However, most MoE models use a fixed top-$k$ expert selection policy, assigning the same expert budget to every token even when fewer experts may be sufficient. Inference-time dynamic top-$k$ routing can reduce computation without retraining, but existing methods often overlook the distributional shift caused by deviating from the training-time routing configuration. We show that reducing the number of activated experts consistently increases the RMS scale and variance of SMoE outputs, inducing a representation mismatch that contributes to downstream performance degradation in addition to the loss of expert capacity. To address this correctable component, we propose Layer-wise Distribution Alignment (LDA), a lightweight inference-time correction that uses layer-wise calibration statistics to align reduced-routing representations with the default configuration. Across multiple SMoE LLMs, benchmarks, and routing strategies, LDA recovers much of the performance lost induced by the distributional shift under reduced routing while preserving sparse-inference efficiency with negligible overhead.

cs.LG↗
arXiv2026

In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Post-Retrieval Context Tampering

Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface: if retrieved text is tampered with, the model may repeat the falsehood. We study how much a small quantized model, Llama 3.1 8B, degrades when a fraction of its retrieved context is poisoned. Three corruption strategies are tested, entity swap, number swap, and negation, each applied to zero, one, two, or three of the three retrieved passages, over a factorial sweep of 588 runs on a fact-checking task built from FEVER. Accuracy falls from 77.9% on clean context to 43.5% when all three passages are corrupted. Entity swap flips the largest share of answers that were correct on clean context. Number-based corruption stays flat while poisoned passages are a minority and jumps once they form a majority, a pattern we re-check with query-level bootstrap intervals. The model rarely invents new falsehoods; its dominant reaction is to abstain, and a lexical overlap proxy of unsupported generation falls under attack rather than rising. The study is a small-scale measurement with coarse automated labels; we treat the strategy contrasts as suggestive until decoding is controlled and stronger adjudication is in place.

cs.CR↗
arXiv2026

StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean

Leading benchmarks for formal theorem proving with large language models are small collections drawn from competition math, such as the IMO and Putnam, that poorly represent field-specific applications. We introduce StochBench, a Lean 4 benchmark of 450 graduate stochastic-processes problems at varying abstraction levels, each paired with its natural-language source. Addressing a field underrepresented in Mathlib, it covers finite and countable Markov chains, renewal processes, random walks, martingales, stopping times, queues, Brownian motion, stochastic calculus, weak convergence, and Poisson and continuous-time Markov processes. Our Opus 4.8-based agent achieves a 34.9% proof rate (157/450) under a 15-minute per-problem limit. StochBench better represents domain-specific applied mathematics while remaining challenging for advanced provers.

cs.CL↗
arXiv2026

Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding

Speculative decoding is critical for accelerating LLM inference. However, the speedup is fragile: drafters are typically trained against a narrow distribution for a single target model, and their acceptance rate collapses under workload shifts. This is a striking inversion of modern LLM development, where target models are valued precisely for the broad generalization they acquire through large-scale pretraining. We argue that the natural remedy, pretraining, has been hard to apply to drafters because existing recipes are target-specific: the drafter consumes the target's hidden states and is distilled on the target's logits, so pretraining must be repeated for each target. We introduce Osprey, which instead bootstraps drafters from off-the-shelf pretrained small language models, treating broad pretraining as a reusable, target-agnostic asset and reducing per-target work to a lightweight adaptation step. Realizing this requires overcoming two challenges: small LMs are far deeper than a latency-bound drafter can afford, and their pretrained computation must remain intact while the drafter learns to ingest target hidden states and emit tokens in the target's vocabulary. Osprey addresses both by pruning to a shallow backbone, restoring its language-modeling capability with target-agnostic next-token pretraining, and adapting it to each target through vocabulary alignment, zero-initialized QKV expansion, and distillation from the target model's output distribution. Empirically, a single pretrained Osprey backbone transfers across targets and improves mean acceptance length by 16.1% for Qwen3-8B, 21.2% for Llama-3.3-70B-Instruct, and 22.7% for the 229B MiniMax-M2.5 (with 17.5% higher tokens per second), with the largest gains on out-of-domain and multilingual data. Our code is available at https://github.com/LeanModels/Osprey.

cs.CL↗
arXiv2026

SWORD: Wikidata-based Distortions Reveal Hidden Cross-Lingual Inconsistencies in LLM Factual Error Rejection

Modern LLMs demonstrate impressive multilingual performance, yet standard benchmarks primarily reward selecting correct answers rather than evaluating genuine factual understanding. We introduce Systematic Wikidata-based Object-Relation Distortion (SWORD), a benchmark that evaluates whether models consistently reject factual errors across languages. SWORD generates syntactically well-formed but factually incorrect statements in eight widely spoken languages through controlled perturbations of Wikidata triples, ranging from random entity substitutions to semantically plausible property-based selections. Our distortion-based evaluation surfaces two critical insights that remain entirely obscured by conventional benchmarks. First, models counterintuitively achieve higher accuracy on semantically plausible distortions than on nonsensical random substitutions, suggesting reliance on distributional familiarity rather than genuine factual verification. Second, models exhibiting comparable baseline accuracy across languages show substantial performance degradation specifically on (East) Asian languages when presented with distorted statements, with cross-lingual performance gaps reaching up to 28 percentage points (49\% relative reduction) in some models. These findings demonstrate that multilingual factual reasoning involves asymmetric capabilities that aggregate accuracy metrics systematically obscure.

cs.CL↗
Compare source metadata on this page
WorkPublishedSource identifierSource
The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits2026-09-082609.09048arxiv
Performance of Clinical AI System and Physicians and Frontier Language Models in primary care diagnostics2026-09-082609.09070arxiv
ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback2026-09-082609.09072arxiv
ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation2026-09-082609.09076arxiv
It's Not RoPE that Creates Sinks: The Role of Self-Concentration and Value-Non-Mixing in Attention2026-09-082609.09085arxiv
SPINE: Measuring LLM Sycophancy under Sustained Multi-Turn Pressure2026-10-132609.09090arxiv
ExecCritic: Learn to Test, Test to Improve for Coding Agents2026-09-082609.09133arxiv
Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation2026-09-082609.09135arxiv
A Data-Driven Framework for Identifying and Prioritizing RPA Opportunities in Healthcare Processes2026-09-082609.09137arxiv
Studying Image Tokenizers as Visual Languages in Unified Multimodal Models2026-09-082609.09143arxiv
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents2026-09-082609.09153arxiv
ReCite: Agentic Reasoning for Faithful Citation2026-09-082609.09156arxiv
Learning Length-Extrapolatable Recurrent Models2026-09-082609.09157arxiv
Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts2026-09-082609.09241arxiv
In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Post-Retrieval Context Tampering2026-09-262609.09243arxiv
StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean2026-09-082609.09264arxiv
Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding2026-09-082609.09338arxiv
SWORD: Wikidata-based Distortions Reveal Hidden Cross-Lingual Inconsistencies in LLM Factual Error Rejection2026-09-082609.09349arxiv

These are bibliographic comparisons, not experimental rankings. Follow the original document for methods and conditions.