{"total":25,"rows":[{"id":"2508.04826","title":"Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History","created":"2025-08-06","cited_by_count":26,"area":"lr"},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"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":"2601.10825","title":"Reasoning Models Generate Societies of Thought","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"id":"2511.08525","title":"Investigating CoT Monitorability in Large Reasoning Models","created":"2025-11-11","cited_by_count":9,"area":"lr"},{"id":"2603.16643","title":"Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy","created":"2026-03-17","cited_by_count":8,"area":"lr"},{"id":"2510.15987","title":"AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2601.09269","title":"RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering","created":"2026-01-14","cited_by_count":6,"area":"lr"},{"id":"2604.24881","title":"Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate","created":"2026-04-27","cited_by_count":5,"area":"lr"},{"id":"2601.19847","title":"Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering","created":"2026-01-27","cited_by_count":4,"area":"lr"},{"id":"2602.04925","title":"Internalizing LLM Reasoning via Discovery and Replay of Latent Actions","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2606.11172","title":"Predicting Future Behaviors in Reasoning Models Enables Better Steering","created":"2026-06-09","cited_by_count":2,"area":"lr"},{"id":"2602.00707","title":"Self-Guard: Defending Large Reasoning Models via enhanced self-reflection","created":"2026-01-31","cited_by_count":1,"area":"lr"},{"id":"2603.12397","title":"Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors","created":"2026-03-12","cited_by_count":1,"area":"lr"},{"id":"2604.02113","title":"Reliable Control-Point Selection for Steering Reasoning in Large Language Models","created":"2026-04-02","cited_by_count":1,"area":"lr"},{"id":"2605.09159","title":"Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas","created":"2026-05-09","cited_by_count":1,"area":"lr"},{"id":"2603.20620","title":"Reasoning Traces Shape Outputs but Models Won't Say So","created":"2026-03-21","cited_by_count":0,"area":"lr"},{"id":"2605.03609","title":"Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models","created":"2026-05-05","cited_by_count":0,"area":"lr"},{"id":"2605.22902","title":"Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models","created":"2026-05-21","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":"2607.09842","title":"From Direction to Magnitude: How Multimodal Instruction-Tuning Reorganizes the Geometric Encoding of Identity-Specifying Prompts in Transformer Hidden States","created":"2026-07-10","cited_by_count":0,"area":"lr"},{"id":"2608.10537","title":"Measuring Semantic Abstractness of SAE Features via Nonlocality","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.20347","title":"Who Do Language Models Think Is Competent? A Mechanistic Analysis of Occupational Bias","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2609.28682","title":"Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.34056","title":"Steering Language Model Goals with Value Transplant","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}