{"total":58,"rows":[{"id":"2607.10059","title":"AgentAbstain: Do LLM Agents Know When Not to Act?","created":"2026-07-11","cited_by_count":17,"area":"agents"},{"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":"2510.21910","title":"Adversarial D\\'ej\\`a Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks","created":"2025-10-24","cited_by_count":7,"area":"safety"},{"id":"2510.04320","title":"Read the Scene, Not the Script: Outcome-Aware Safety for LLMs","created":"2025-10-05","cited_by_count":6,"area":"alignment"},{"id":"2510.09905","title":"The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs","created":"2025-10-10","cited_by_count":6,"area":"lr"},{"id":"2603.03919","title":"When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG","created":"2026-03-04","cited_by_count":4,"area":"rag"},{"id":"2605.09278","title":"EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium","created":"2026-05-10","cited_by_count":4,"area":"agents"},{"id":"2606.32038","title":"Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision","created":"2026-06-30","cited_by_count":4,"area":null},{"id":"2505.23914","title":"Probing Association Biases in LLM Moderation Over-Sensitivity","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2506.19028","title":"Quantifying Fairness in LLMs Beyond Tokens: A Semantic and Statistical Perspective","created":"2025-06-23","cited_by_count":3,"area":null},{"id":"2509.18293","title":"Evaluating Large Language Models for Detecting Antisemitism","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2602.16729","title":"Intent Laundering: AI Safety Datasets Are Not What They Seem","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2603.03323","title":"Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement","created":"2026-02-10","cited_by_count":3,"area":"safety"},{"id":"2604.10286","title":"STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems","created":"2026-04-11","cited_by_count":3,"area":"agents"},{"id":"2604.27093","title":"Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations","created":"2026-04-29","cited_by_count":3,"area":"alignment"},{"id":"2606.25013","title":"Do Thinking Tokens Help with Safety?","created":"2026-06-23","cited_by_count":3,"area":"lr"},{"id":"2512.01037","title":"How Semantically Stable Are LLM Refusals? Measuring Confusion in Local Safety Boundaries","created":"2025-11-30","cited_by_count":2,"area":"alignment"},{"id":"2603.16734","title":"Differential Harm Propensity in Personalized LLM Agents: The Curious Case of Mental Health Disclosure","created":"2026-03-17","cited_by_count":2,"area":"agents"},{"id":"2603.27518","title":"Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs","created":"2026-03-29","cited_by_count":2,"area":"alignment"},{"id":"2604.06233","title":"Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2607.19806","title":"OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization","created":"2026-07-22","cited_by_count":2,"area":"safety"},{"id":"2607.20090","title":"Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results","created":"2026-07-22","cited_by_count":2,"area":"rag"},{"id":"2506.00195","title":"Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences","created":"2025-05-30","cited_by_count":1,"area":"alignment"},{"id":"2511.19009","title":"Understanding and Mitigating Over-refusal for Large Language Models via Representation Intervention","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2602.04521","title":"$C$-$\\Delta\\Theta$: Circuit-Restricted Weight Arithmetic for Selective Refusal","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2605.29468","title":"SciIntBench: Measuring LLM Compliance with Research Integrity Norms Under Adversarial Framing","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2608.23837","title":"SyPS: Measuring Sycophancy Prompt Sensitivity in Large Language Models","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2609.25049","title":"Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration","created":"2026-09-06","cited_by_count":1,"area":"safety"},{"id":"2508.11290","title":"SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering","created":"2025-08-15","cited_by_count":0,"area":"safety"},{"id":"2509.05367","title":"Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs","created":"2025-09-04","cited_by_count":0,"area":"lr"},{"id":"2602.02027","title":"Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2604.07709","title":"IatroBench: A Pre-Registered Benchmark of Clinical Omission in Language Models","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.10990","title":"When Verification Fails: How Compositionally Infeasible Claims Escape Rejection","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.01831","title":"RMGAP: Benchmarking the Generalization of Reward Models across Diverse Preferences","created":"2026-05-03","cited_by_count":0,"area":"alignment"},{"id":"2605.05630","title":"One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.06213","title":"Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2605.20262","title":"Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.23974","title":"AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.12923","title":"Order Is Not Control: Driven-Dissipative Response Laws Across Artificial and Biological Systems","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.13737","title":"FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization","created":"2026-06-11","cited_by_count":0,"area":"safety"},{"id":"2606.16349","title":"From Refusal Geometry to Safety Geometry: Harmfulness--Refusal Coupling under Dynamic Adversarial Fine-Tuning","created":"2026-06-15","cited_by_count":0,"area":"alignment"},{"id":"2606.29581","title":"The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis","created":"2026-06-28","cited_by_count":0,"area":"alignment"},{"id":"2606.31748","title":"Addressing Over-Refusal in LLMs with Competing Rewards","created":"2026-06-30","cited_by_count":0,"area":"safety"},{"id":"2607.20472","title":"Robust Critics: Defending LLMs Against Multi-Turn Attacks","created":"2026-05-24","cited_by_count":0,"area":"safety"},{"id":"2608.13304","title":"Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety","created":"2026-08-13","cited_by_count":0,"area":"safety"},{"id":"2608.22490","title":"Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across Languages","created":"2026-08-23","cited_by_count":0,"area":"alignment"},{"id":"2608.23568","title":"RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2609.00760","title":"A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.02707","title":"Door-in-the-Face Requests and Refusal Behaviour in Large Language Models","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.04482","title":"Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2609.04714","title":"Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models","created":"2026-09-04","cited_by_count":0,"area":"alignment"},{"id":"2609.14157","title":"When Tools Get in the Way: The Effect of Unnecessary Tool Availability on LLM Answering","created":"2026-09-12","cited_by_count":0,"area":"agents"},{"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":"2609.32602","title":"AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion","created":"2026-09-26","cited_by_count":0,"area":"safety"},{"id":"2609.34896","title":"DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models","created":"2026-09-28","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":"2609.37807","title":"CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.19968","title":"Safe-FCL: Continual Risk Awareness and Fine-Grained Safety Aggregation for Federated Continual Learning of LLMs","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}