{"total":20,"rows":[{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2506.10597","title":"SoK: Evaluating Jailbreak Guardrails for Large Language Models","created":"2025-06-12","cited_by_count":21,"area":"alignment"},{"id":"2602.01539","title":"MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety","created":"2026-02-02","cited_by_count":21,"area":"alignment"},{"id":"2510.05052","title":"Proactive defense against LLM Jailbreak","created":"2025-10-06","cited_by_count":7,"area":"alignment"},{"id":"2511.19517","title":"Automating Deception: Scalable Multi-Turn LLM Jailbreaks","created":"2025-11-24","cited_by_count":7,"area":"alignment"},{"id":"2510.08646","title":"Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy","created":"2025-10-09","cited_by_count":5,"area":"alignment"},{"id":"2603.15684","title":"State-Dependent Safety Failures in Multi-Turn Language Model Interaction","created":"2026-03-15","cited_by_count":4,"area":"alignment"},{"id":"2602.04448","title":"RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models","created":"2026-02-04","cited_by_count":3,"area":"alignment"},{"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":"2604.16916","title":"When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints","created":"2026-04-18","cited_by_count":2,"area":"alignment"},{"id":"2606.06797","title":"Korean Culture into LLM Alignment: Toward Cultural Coherence","created":"2026-06-05","cited_by_count":2,"area":"alignment"},{"id":"2509.22732","title":"Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks","created":"2025-09-25","cited_by_count":1,"area":"alignment"},{"id":"2604.15717","title":"Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries","created":"2026-04-17","cited_by_count":1,"area":"alignment"},{"id":"2603.18637","title":"MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment","created":"2026-03-19","cited_by_count":0,"area":"alignment"},{"id":"2605.08277","title":"Mitigating Many-shot Jailbreak Attacks with One Single Demonstration","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2608.09551","title":"Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2609.04022","title":"Representational alignment yields generalizable safety in language models","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2609.38389","title":"The Geometry of Harmfulness in Multi-Turn Attacks","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2610.01323","title":"TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety","created":"2026-10-01","cited_by_count":0,"area":"alignment"},{"id":"2610.12233","title":"ReSI: Recursive Safety Improvement toward Resistant and Resilient AI","created":"2026-10-08","cited_by_count":0,"area":"alignment"}],"next_cursor":null}