{"total":48,"rows":[{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386,"area":"lr"},{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244,"area":"lr"},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122,"area":"lr"},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308,"area":"lr"},{"id":"2212.08061","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","created":"2022-12-15","cited_by_count":194,"area":"lr"},{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145,"area":"lr"},{"id":"2501.08156","title":"Are DeepSeek R1 And Other Reasoning Models More Faithful?","created":"2025-01-14","cited_by_count":72,"area":"lr"},{"id":"2507.14417","title":"Inverse Scaling in Test-Time Compute","created":"2025-07-19","cited_by_count":50,"area":"lr"},{"id":"2405.18634","title":"A Theoretical Understanding of Self-Correction through In-context Alignment","created":"2024-05-28","cited_by_count":44,"area":"lr"},{"id":"2308.10855","title":"LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles","created":"2023-08-21","cited_by_count":41,"area":"lr"},{"id":"2505.14617","title":"The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness","created":"2025-05-20","cited_by_count":30,"area":"lr"},{"id":"2210.07269","title":"SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models","created":"2022-10-13","cited_by_count":22,"area":"lr"},{"id":"2604.17073","title":"Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL","created":"2026-04-18","cited_by_count":14,"area":"lr"},{"id":"2602.02639","title":"A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior","created":"2026-02-02","cited_by_count":13,"area":"lr"},{"id":"2311.13063","title":"From Classification to Clinical Insights: Towards Analyzing and Reasoning About Mobile and Behavioral Health Data With Large Language Models","created":"2023-11-21","cited_by_count":11,"area":"lr"},{"id":"2406.04215","title":"mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans","created":"2024-06-06","cited_by_count":10,"area":"lr"},{"id":"2507.11344","title":"Guiding LLM Decision-Making with Fairness Reward Models","created":"2025-07-15","cited_by_count":9,"area":"lr"},{"id":"2507.20187","title":"Diversity-Enhanced Reasoning for Subjective Questions","created":"2025-07-27","cited_by_count":9,"area":"lr"},{"id":"2503.01539","title":"Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language","created":"2025-03-03","cited_by_count":8,"area":"lr"},{"id":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","cited_by_count":8,"area":"lr"},{"id":"2602.10117","title":"Biases in the Blind Spot: Detecting What LLMs Fail to Mention","created":"2026-02-10","cited_by_count":8,"area":"lr"},{"id":"2503.00093","title":"Rethinking LLM Bias Probing Using Lessons from the Social Sciences","created":"2025-02-28","cited_by_count":7,"area":"lr"},{"id":"2305.06841","title":"Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models","created":"2023-05-11","cited_by_count":6,"area":"lr"},{"id":"2508.20737","title":"Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol","created":"2025-08-28","cited_by_count":6,"area":"lr"},{"id":"2602.24014","title":"Interpretable Debiasing of Vision-Language Models for Social Fairness","created":"2026-02-27","cited_by_count":6,"area":"lr"},{"id":"2507.00004","title":"A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search","created":"2025-06-10","cited_by_count":5,"area":"lr"},{"id":"2508.06361","title":"Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts","created":"2025-08-08","cited_by_count":5,"area":"lr"},{"id":"2510.24236","title":"Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?","created":"2025-10-28","cited_by_count":5,"area":"lr"},{"id":"2503.18394","title":"Solving Situation Puzzles with Large Language Model and External Reformulation","created":"2025-03-24","cited_by_count":4,"area":"lr"},{"id":"2504.21299","title":"BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models","created":"2025-04-30","cited_by_count":4,"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":"2510.14200","title":"RLSR: Reinforcement Learning with Supervised Reward Outperforms SFT in Instruction Following","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2601.18760","title":"Beyond Preferences: Learning Alignment Principles Grounded in Human Reasons and Values","created":"2026-01-26","cited_by_count":1,"area":"lr"},{"id":"2605.17826","title":"CounterCount: A Diagnostic Framework for Counting Bias in Vision Language Models","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2407.12007","title":"People will agree what I think: Investigating LLM's False Consensus Effect","created":"2024-06-16","cited_by_count":0,"area":"lr"},{"id":"2505.12896","title":"On the Thinking-Language Modeling Gap in Large Language Models","created":"2025-05-19","cited_by_count":0,"area":"lr"},{"id":"2511.06023","title":"Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data","created":"2025-11-08","cited_by_count":0,"area":"lr"},{"id":"2512.03082","title":"Alleviating Choice Supportive Bias in LLM with Reasoning Dependency Generation","created":"2025-11-28","cited_by_count":0,"area":"lr"},{"id":"2604.02230","title":"Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2605.02348","title":"Decoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended Generation","created":"2026-05-04","cited_by_count":0,"area":"lr"},{"id":"2605.20410","title":"Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2606.10931","title":"It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.16562","title":"MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2606.28615","title":"What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2607.20448","title":"Domyn-Small: A European 10B Reasoning Language Model","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2608.14161","title":"BiasTrace: Linking Reasoning Behaviours to Biased Outputs in LLMs","created":"2026-08-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}