{"total":19,"rows":[{"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":"2505.12189","title":"Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering","created":"2025-05-18","cited_by_count":18,"area":"lr"},{"id":"2504.17130","title":"Steering the CensorShip: Uncovering Representation Vectors for LLM \"Thought\" Control","created":"2025-04-23","cited_by_count":14,"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":"2510.05498","title":"Prototype-Based Dynamic Steering for Large Language Models","created":"2025-10-07","cited_by_count":6,"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":"2605.05980","title":"TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering","created":"2026-05-07","cited_by_count":6,"area":"lr"},{"id":"2506.21590","title":"Representation Consistency for Accurate and Coherent LLM Answer Aggregation","created":"2025-06-18","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":"2511.19131","title":"Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization","created":"2025-11-24","cited_by_count":2,"area":"lr"},{"id":"2604.01202","title":"Therefore I am. I Think","created":"2026-04-01","cited_by_count":2,"area":"lr"},{"id":"2607.01433","title":"CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse","created":"2026-07-01","cited_by_count":2,"area":"lr"},{"id":"2605.05678","title":"Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.27932","title":"When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2603.16331","title":"Decoding the Critique Mechanism in Large Reasoning Models","created":"2026-03-17","cited_by_count":0,"area":"lr"},{"id":"2605.29888","title":"LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2608.14465","title":"You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model","created":"2026-08-14","cited_by_count":0,"area":"lr"},{"id":"2608.30462","title":"Enhancing Low-Resource Language Reasoning via High-Resource Language Feature Transfer","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2610.01595","title":"Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}