{"total":49,"rows":[{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050,"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":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194,"area":"lr"},{"id":"2306.15448","title":"Understanding Social Reasoning in Language Models with Language Models","created":"2023-06-21","cited_by_count":172,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"area":"lr"},{"id":"2402.06044","title":"OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models","created":"2024-02-08","cited_by_count":54,"area":"lr"},{"id":"2411.18688","title":"Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment","created":"2024-11-27","cited_by_count":44,"area":"lr"},{"id":"2503.05021","title":"Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety","created":"2025-03-06","cited_by_count":39,"area":"lr"},{"id":"2502.01633","title":"Adversarial Reasoning at Jailbreaking Time","created":"2025-02-03","cited_by_count":29,"area":"lr"},{"id":"2503.18929","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","created":"2025-03-24","cited_by_count":29,"area":"lr"},{"id":"2301.00355","title":"Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits","created":"2023-01-01","cited_by_count":27,"area":"lr"},{"id":"2603.05706","title":"Reasoning Models Struggle to Control their Chains of Thought","created":"2026-03-05","cited_by_count":25,"area":"lr"},{"id":"2308.09853","title":"How susceptible are LLMs to Logical Fallacies?","created":"2023-08-18","cited_by_count":23,"area":"lr"},{"id":"2503.01781","title":"Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models","created":"2025-03-03","cited_by_count":23,"area":"lr"},{"id":"2401.17882","title":"I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench","created":"2024-01-31","cited_by_count":21,"area":"lr"},{"id":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","cited_by_count":21,"area":"lr"},{"id":"2508.04039","title":"Large Reasoning Models Are Autonomous Jailbreak Agents","created":"2025-08-04","cited_by_count":13,"area":"lr"},{"id":"2511.01191","title":"Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning","created":"2025-11-03","cited_by_count":10,"area":"lr"},{"id":"2410.21791","title":"Enhancing Adversarial Attacks through Chain of Thought","created":"2024-10-29","cited_by_count":8,"area":"lr"},{"id":"2505.16241","title":"Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers","created":"2025-05-22","cited_by_count":8,"area":"lr"},{"id":"2602.07186","title":"The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization","created":"2026-02-06","cited_by_count":8,"area":"lr"},{"id":"2505.10846","title":"AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models","created":"2025-05-16","cited_by_count":7,"area":"lr"},{"id":"2506.13726","title":"Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models","created":"2025-06-16","cited_by_count":7,"area":"lr"},{"id":"2506.19257","title":"MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models","created":"2025-06-24","cited_by_count":7,"area":"lr"},{"id":"2606.09701","title":"Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO","created":"2026-06-08","cited_by_count":5,"area":"lr"},{"id":"2502.04357","title":"Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs","created":"2025-02-04","cited_by_count":4,"area":"lr"},{"id":"2510.04141","title":"The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation from Recognition to Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2510.17687","title":"CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks","created":"2025-10-20","cited_by_count":4,"area":"lr"},{"id":"2604.00304","title":"Asymmetric Actor-Critic for Multi-turn LLM Agents","created":"2026-03-31","cited_by_count":4,"area":"lr"},{"id":"2402.08498","title":"\"Reasoning\" with Rhetoric: On the Style-Evidence Tradeoff in LLM-Generated Counter-Arguments","created":"2024-02-13","cited_by_count":2,"area":"lr"},{"id":"2509.21401","title":"JaiLIP: Jailbreaking Vision-Language Models via Loss Guided Image Perturbation","created":"2025-09-24","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":"2602.11792","title":"Detecting RLVR Training Data via Structural Convergence of Reasoning","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2604.25684","title":"Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents","created":"2026-04-28","cited_by_count":2,"area":"lr"},{"id":"2606.01441","title":"Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts","created":"2026-05-31","cited_by_count":2,"area":"lr"},{"id":"2406.19552","title":"Rethinking harmless refusals when fine-tuning foundation models","created":"2024-06-27","cited_by_count":1,"area":"lr"},{"id":"2602.01689","title":"What LLMs Think When You Don't Tell Them What to Think About?","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2604.19001","title":"HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2605.08427","title":"The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.11599","title":"Targeted Tests for LLM Reasoning: An Audit-Constrained Protocol","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2606.08234","title":"SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents","created":"2026-06-06","cited_by_count":1,"area":"lr"},{"id":"2510.01569","title":"InvThink: Premortem Reasoning for Safer Language Models","created":"2025-10-02","cited_by_count":0,"area":"lr"},{"id":"2602.06650","title":"Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought","created":"2026-02-06","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":"2605.17278","title":"A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation","created":"2026-05-17","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":"2608.09542","title":"Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs","created":"2026-08-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}