{"total":46,"rows":[{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2502.13295","title":"Demonstrating specification gaming in reasoning models","created":"2025-02-18","cited_by_count":56,"area":"lr"},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29,"area":"lr"},{"id":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26,"area":"lr"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"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":"2505.21479","title":"Are Language Models Consequentialist or Deontological Moral Reasoners?","created":"2025-05-27","cited_by_count":12,"area":"lr"},{"id":"2409.00399","title":"Rethinking Backdoor Detection Evaluation for Language Models","created":"2024-08-31","cited_by_count":9,"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":"2512.11949","title":"Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors","created":"2025-12-12","cited_by_count":9,"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":"2505.19690","title":"Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2509.17938","title":"D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models","created":"2025-09-22","cited_by_count":7,"area":"lr"},{"id":"2510.08710","title":"Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning","created":"2025-10-09","cited_by_count":7,"area":"lr"},{"id":"2504.10615","title":"Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models","created":"2025-04-14","cited_by_count":6,"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":"2510.15965","title":"One Token Embedding Is Enough to Deadlock Your Large Reasoning Model","created":"2025-10-12","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":"2607.22925","title":"Not All LLM Reasoning is Visible in the Chain-of-Thought","created":"2026-07-24","cited_by_count":5,"area":"lr"},{"id":"2603.26410","title":"Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models","created":"2026-03-27","cited_by_count":4,"area":"lr"},{"id":"2510.00319","title":"DecepChain: Inducing Deceptive Reasoning in Large Language Models","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2603.15661","title":"DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2606.07054","title":"TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents","created":"2026-06-05","cited_by_count":3,"area":"lr"},{"id":"2412.03904","title":"MISR: Measuring Instrumental Self-Reasoning in Frontier Models","created":"2024-12-05","cited_by_count":2,"area":"lr"},{"id":"2510.19476","title":"A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring","created":"2025-10-22","cited_by_count":2,"area":"lr"},{"id":"2604.23460","title":"Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"id":"2604.28182","title":"Exploration Hacking: Can LLMs Learn to Resist RL Training?","created":"2026-04-30","cited_by_count":2,"area":"lr"},{"id":"2605.01704","title":"The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning","created":"2026-05-03","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":"2406.19552","title":"Rethinking harmless refusals when fine-tuning foundation models","created":"2024-06-27","cited_by_count":1,"area":"lr"},{"id":"2509.19775","title":"bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2603.09200","title":"The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2604.00770","title":"Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent Reasoning","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2604.09665","title":"Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2604.22119","title":"Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework","created":"2026-04-23","cited_by_count":1,"area":"lr"},{"id":"2605.17113","title":"The Point of No Return: Counterfactual Localization of Deceptive Commitment in Language-Model Reasoning","created":"2026-05-16","cited_by_count":1,"area":"lr"},{"id":"2607.08173","title":"Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets","created":"2026-07-09","cited_by_count":1,"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":"2603.26846","title":"Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry","created":"2026-03-27","cited_by_count":0,"area":"lr"},{"id":"2605.28825","title":"MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2606.10740","title":"When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models","created":"2026-06-09","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":"2608.15445","title":"Measuring Reward Hacking and Reasoning-Answer Decoupling Under Position-Confounded Optimization","created":"2026-08-15","cited_by_count":0,"area":"lr"},{"id":"2609.36254","title":"Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.04737","title":"PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution","created":"2026-10-03","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"}],"next_cursor":null}