{"total":96,"rows":[{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159,"area":"lr"},{"id":"2412.14959","title":"Understanding the Dark Side of LLMs' Intrinsic Self-Correction","created":"2024-12-19","cited_by_count":42,"area":"lr"},{"id":"2403.05518","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","created":"2024-03-08","cited_by_count":39,"area":"lr"},{"id":"2506.01926","title":"Large language models can learn and generalize steganographic chain-of-thought under process supervision","created":"2025-06-02","cited_by_count":32,"area":"lr"},{"id":"2510.19851","title":"Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability","created":"2025-10-21","cited_by_count":22,"area":"lr"},{"id":"2506.07180","title":"Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs","created":"2025-06-08","cited_by_count":21,"area":"lr"},{"id":"2405.00622","title":"Causal Evaluation of Language Models","created":"2024-05-01","cited_by_count":18,"area":"lr"},{"id":"2510.27378","title":"Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity","created":"2025-10-31","cited_by_count":17,"area":"lr"},{"id":"2502.09192","title":"Thinking beyond the anthropomorphic paradigm benefits LLM research","created":"2025-02-13","cited_by_count":14,"area":"lr"},{"id":"2505.17815","title":"Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems","created":"2025-05-23","cited_by_count":14,"area":"lr"},{"id":"2507.11662","title":"Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification","created":"2025-07-15","cited_by_count":14,"area":"lr"},{"id":"2506.20020","title":"Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning","created":"2025-06-24","cited_by_count":13,"area":"lr"},{"id":"2511.06419","title":"MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models","created":"2025-11-09","cited_by_count":12,"area":"lr"},{"id":"2509.16742","title":"Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories","created":"2025-09-20","cited_by_count":11,"area":"lr"},{"id":"2609.31142","title":"JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models","created":"2026-09-25","cited_by_count":10,"area":"lr"},{"id":"2504.05294","title":"Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations","created":"2025-04-07","cited_by_count":9,"area":"lr"},{"id":"2603.06621","title":"Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models","created":"2026-02-20","cited_by_count":9,"area":"lr"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2603.22582","title":"Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2606.00820","title":"Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate","created":"2026-05-30","cited_by_count":7,"area":"lr"},{"id":"2506.09677","title":"Benchmarking Gaslighting Negation Attacks Against Reasoning Models","created":"2025-06-11","cited_by_count":6,"area":"lr"},{"id":"2604.07667","title":"From Debate to Decision: Conformal Social Choice for Safe Multi-Agent Deliberation","created":"2026-04-09","cited_by_count":6,"area":"lr"},{"id":"2410.01545","title":"Lines of Thought in Large Language Models","created":"2024-10-02","cited_by_count":5,"area":"lr"},{"id":"2504.20157","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","created":"2025-04-28","cited_by_count":5,"area":"lr"},{"id":"2509.15557","title":"Reward Hacking Mitigation using Verifiable Composite Rewards","created":"2025-09-19","cited_by_count":5,"area":"lr"},{"id":"2512.02914","title":"Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning","created":"2025-12-02","cited_by_count":5,"area":"lr"},{"id":"2601.08258","title":"Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment","created":"2026-01-13","cited_by_count":5,"area":"lr"},{"id":"2509.20553","title":"Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation","created":"2025-09-24","cited_by_count":4,"area":"lr"},{"id":"2512.10080","title":"What Kind of Reasoning (if any) is an LLM actually doing? On the Stochastic Nature and Abductive Appearance of Large Language Models","created":"2025-12-10","cited_by_count":4,"area":"lr"},{"id":"2602.04288","title":"Contextual Drag: How Errors in the Context Affect LLM Reasoning","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2602.13093","title":"Consistency of Large Reasoning Models Under Multi-Turn Attacks","created":"2026-02-13","cited_by_count":4,"area":"lr"},{"id":"2603.20172","title":"Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation","created":"2026-03-20","cited_by_count":4,"area":"lr"},{"id":"2601.21183","title":"Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2604.08243","title":"Self-Debias: Self-correcting for Debiasing Large Language Models","created":"2026-04-09","cited_by_count":3,"area":"lr"},{"id":"2605.02269","title":"Towards Understanding Specification Gaming in Reasoning Models","created":"2026-05-04","cited_by_count":3,"area":"lr"},{"id":"2608.01017","title":"Why LLMs Give In: Conversational Factors and Reasoning Behind Medical Sycophancy","created":"2026-08-02","cited_by_count":3,"area":"lr"},{"id":"2511.00379","title":"Diverse Human Value Alignment for Large Language Models via Ethical Reasoning","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2512.10687","title":"Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users","created":"2025-12-11","cited_by_count":2,"area":"lr"},{"id":"2601.12019","title":"Acting Flatterers via LLMs Sycophancy: Combating Clickbait with LLMs Opposing-Stance Reasoning","created":"2026-01-17","cited_by_count":2,"area":"lr"},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2602.02496","title":"The Hypocrisy Gap: Quantifying Divergence Between Internal Belief and Chain-of-Thought Explanation via Sparse Autoencoders","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2602.03994","title":"Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2602.08939","title":"CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2602.11675","title":"Epistemic Regret Minimization: Label-Free Causal Critique Beyond Outcome Reward","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2603.04663","title":"Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detector","created":"2026-03-04","cited_by_count":2,"area":"lr"},{"id":"2604.19656","title":"Pause or Fabricate? Training Language Models for Grounded Reasoning","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2605.10799","title":"The Last Word Often Wins: A Format Confound in Chain-of-Thought Corruption Studies","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2606.05976","title":"The Self-Correction Illusion: Role Relabeling Gates Explicit Error Flagging in Large Language Models","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.17478","title":"Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing","created":"2026-06-16","cited_by_count":2,"area":"lr"},{"id":"2607.08066","title":"Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2607.21558","title":"Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning","created":"2026-07-23","cited_by_count":2,"area":"lr"},{"id":"2410.13216","title":"Anchored Alignment for Self-Explanations Enhancement","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2509.13345","title":"Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2601.01490","title":"Distortion Instead of Hallucination: The Effect of Reasoning Under Strict Constraints","created":"2026-01-04","cited_by_count":1,"area":"lr"},{"id":"2602.14518","title":"Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2605.16301","title":"Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2606.12730","title":"Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2606.13220","title":"LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis","created":"2026-06-11","cited_by_count":1,"area":"lr"},{"id":"2606.18327","title":"Self-CTRL: Self-Consistency Training with Reinforcement Learning","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2606.24251","title":"Probing the Misaligned Thinking Process of Language Models","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2606.29654","title":"Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds","created":"2026-06-28","cited_by_count":1,"area":"lr"},{"id":"2607.01951","title":"Robust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science Skepticism","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2607.23458","title":"Two Regimes of Chain-of-Thought Unfaithfulness: Metric-Based Detection Fails Where Models Are Wrong","created":"2026-07-26","cited_by_count":1,"area":"lr"},{"id":"2608.28623","title":"Looking Again: Measuring Sycophancy in the Reasoning Chains of Multimodal Models Under Pressure","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2609.17496","title":"Verifiable Social Reasoning for LLM Assistants","created":"2026-09-15","cited_by_count":1,"area":"lr"},{"id":"2505.22767","title":"In Dialogue with Intelligence: Rethinking Large Language Models as Collective Knowledge","created":"2025-05-28","cited_by_count":0,"area":"lr"},{"id":"2507.23170","title":"BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning","created":"2025-07-31","cited_by_count":0,"area":"lr"},{"id":"2508.15839","title":"CIA+TA Risk Assessment for AI Reasoning Vulnerabilities","created":"2025-08-19","cited_by_count":0,"area":"lr"},{"id":"2509.22876","title":"HEART: Emotionally-Driven Test-Time Scaling of Language Models","created":"2025-09-26","cited_by_count":0,"area":"lr"},{"id":"2601.00830","title":"Can We Trust AI Explanations? Evidence of Systematic Underreporting in Chain-of-Thought Reasoning","created":"2025-12-25","cited_by_count":0,"area":"lr"},{"id":"2602.01528","title":"Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement Learning","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.06446","title":"CORE: Comprehensive Ontological Relation Evaluation for Large Language Models","created":"2026-02-06","cited_by_count":0,"area":"lr"},{"id":"2602.17127","title":"The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI","created":"2026-02-19","cited_by_count":0,"area":"lr"},{"id":"2603.09987","title":"Evolving Demonstration Optimization for Chain-of-Thought Feature Transformation","created":"2026-02-13","cited_by_count":0,"area":"lr"},{"id":"2603.17822","title":"Multi-Source Evidence Fusion for Audio Question Answering","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2603.22730","title":"How Utilitarian Are OpenAI's Models Really? Replicating and Reinterpreting Pfeffer, Kr\\\"ugel, and Uhl (2025)","created":"2026-03-24","cited_by_count":0,"area":"lr"},{"id":"2604.12076","title":"Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2604.16913","title":"The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus","created":"2026-04-18","cited_by_count":0,"area":"lr"},{"id":"2605.03900","title":"Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems","created":"2026-05-05","cited_by_count":0,"area":"lr"},{"id":"2605.07138","title":"Can You Break RLVER? Probing Adversarial Robustness of RL-Trained Empathetic Agents","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.18799","title":"ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2606.07515","title":"How reliable are LLMs when it comes to playing dice?","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2606.11635","title":"Are LLMs Bad at Moral Reasoning?","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.26366","title":"Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"id":"2607.01581","title":"Beyond Skepticism: Evaluating LLMs Pedagogical Intent Reasoning with the Adaptive Pedagogical Vigilance Framework","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.10411","title":"Mitigating LLM Sycophancy in Code Smell Detection Using Evidence-Guided Reasoning Prompts","created":"2026-07-11","cited_by_count":0,"area":"lr"},{"id":"2607.12480","title":"TRACE: An Operational Reasoning Schema for Auditable Agentic Commitments","created":"2026-07-14","cited_by_count":0,"area":"lr"},{"id":"2607.14099","title":"Just Keep Prompting: Evaluating Repetitive Socratic Prompting in VLMs","created":"2026-05-01","cited_by_count":0,"area":"lr"},{"id":"2609.02754","title":"Untangling the Mechanisms of Misleading Context in Medical Question Answering","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2609.05088","title":"Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?","created":"2026-09-04","cited_by_count":0,"area":"lr"},{"id":"2609.23205","title":"Euston: Training Away Mathematical Sycophancy Without Losing the Mathematics","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"id":"2610.01222","title":"Reputation, Strategy, and Emotion Effects on Generative AI Cooperation: A Comparison Across Reasoning and Non-Reasoning Models","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.04914","title":"Monitorability Disposition in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.05472","title":"Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.16170","title":"Geometric Parrots: Rule Absence vs. Rule Fragility in Spatial and Physical Reasoning for Vision-Language Models","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}