{"total":61,"rows":[{"id":"2506.18167","title":"Understanding Reasoning in Thinking Language Models via Steering Vectors","created":"2025-06-22","cited_by_count":72,"area":"lr"},{"id":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58,"area":"lr"},{"id":"2502.09674","title":"The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions","created":"2025-02-13","cited_by_count":41,"area":"lr"},{"id":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40,"area":"lr"},{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"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":"2510.07364","title":"Base Models Know How to Reason, Thinking Models Learn When","created":"2025-10-08","cited_by_count":27,"area":"lr"},{"id":"2507.12638","title":"Reasoning-Finetuning Repurposes Latent Representations in Base Models","created":"2025-07-16","cited_by_count":26,"area":"lr"},{"id":"2503.23084","title":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","created":"2025-03-29","cited_by_count":21,"area":"lr"},{"id":"2507.02778","title":"Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models","created":"2025-07-03","cited_by_count":20,"area":"lr"},{"id":"2601.15588","title":"YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models","created":"2026-01-22","cited_by_count":19,"area":"lr"},{"id":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"area":"lr"},{"id":"2507.12428","title":"Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models","created":"2025-07-16","cited_by_count":17,"area":"lr"},{"id":"2505.20087","title":"Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models","created":"2025-05-26","cited_by_count":16,"area":"lr"},{"id":"2605.12400","title":"OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning","created":"2026-05-12","cited_by_count":16,"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":"2602.09924","title":"LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations","created":"2026-02-10","cited_by_count":14,"area":"lr"},{"id":"2504.02010","title":"When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models","created":"2025-04-02","cited_by_count":13,"area":"lr"},{"id":"2504.14379","title":"The Geometry of Self-Verification in a Task-Specific Reasoning Model","created":"2025-04-19","cited_by_count":13,"area":"lr"},{"id":"2506.08390","title":"On Reasoning Strength Planning in Large Reasoning Models","created":"2025-06-10","cited_by_count":13,"area":"lr"},{"id":"2506.07335","title":"Improving LLM Reasoning through Interpretable Role-Playing Steering","created":"2025-06-09","cited_by_count":12,"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":"2410.03595","title":"Understanding Reasoning in Chain-of-Thought from the Hopfieldian View","created":"2024-10-04","cited_by_count":11,"area":"lr"},{"id":"2511.04527","title":"Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics","created":"2025-11-06","cited_by_count":11,"area":"lr"},{"id":"2512.12069","title":"Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring","created":"2025-12-12","cited_by_count":11,"area":"lr"},{"id":"2510.00404","title":"AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2511.08525","title":"Investigating CoT Monitorability in Large Reasoning Models","created":"2025-11-11","cited_by_count":9,"area":"lr"},{"id":"2506.15647","title":"Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement","created":"2025-06-18","cited_by_count":8,"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":"2603.17998","title":"The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering","created":"2026-03-18","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":"2602.00154","title":"ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models","created":"2026-01-29","cited_by_count":5,"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":"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":"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":"2503.17365","title":"How Effective Is Constitutional AI in Small LLMs? A Study on DeepSeek-R1 and Its Peers","created":"2025-02-01","cited_by_count":3,"area":"lr"},{"id":"2510.22437","title":"Modeling Hierarchical Thinking in Large Reasoning Models","created":"2025-10-25","cited_by_count":3,"area":"lr"},{"id":"2603.14636","title":"Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models","created":"2026-03-15","cited_by_count":2,"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":"2604.06377","title":"The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment","created":"2026-04-07","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":"2604.19001","title":"HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2605.27932","title":"When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2607.01951","title":"Robust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science Skepticism","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2607.15286","title":"Hidden in Thought: Transferable Chain-of-Thought Artifacts Induce Harmful Behavior","created":"2026-06-18","cited_by_count":1,"area":"lr"},{"id":"2508.11272","title":"Enhancing Supervised Composed Image Retrieval via Reasoning-Augmented Representation Engineering","created":"2025-08-15","cited_by_count":0,"area":"lr"},{"id":"2509.08358","title":"<think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs","created":"2025-09-10","cited_by_count":0,"area":"lr"},{"id":"2605.26772","title":"Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2605.28467","title":"Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training","created":"2026-05-27","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":"2607.27594","title":"Compliance2LoRA: Personalizable On-Demand Safety Alignment on Arbitrary Policy Subsets via Hypernetwork-Generated LoRA Adapters","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2607.28146","title":"Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.00583","title":"A False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragility","created":"2026-08-01","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":"2608.18628","title":"When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.23497","title":"Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2608.28859","title":"The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.27763","title":"Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2609.34344","title":"Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.14270","title":"The Thinking Leakage in Reinforcement Learning for LLMs","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.18127","title":"Monitoring latent reasoning in looped language models","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}