{"total":18,"rows":[{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2501.13381","title":"Do as We Do, Not as You Think: the Conformity of Large Language Models","created":"2025-01-23","cited_by_count":53,"area":"lr"},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29,"area":"lr"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2505.18154","title":"The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas","created":"2025-05-23","cited_by_count":13,"area":"lr"},{"id":"2505.19241","title":"ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment","created":"2025-05-25","cited_by_count":10,"area":"lr"},{"id":"2510.06871","title":"SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models","created":"2025-10-08","cited_by_count":10,"area":"lr"},{"id":"2406.16061","title":"PORT: Preference Optimization on Reasoning Traces","created":"2024-06-23","cited_by_count":6,"area":"lr"},{"id":"2407.17963","title":"Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning Tasks","created":"2024-07-25","cited_by_count":5,"area":"lr"},{"id":"2505.23436","title":"Emergent Risk Awareness in Rational Agents under Resource Constraints","created":"2025-05-29","cited_by_count":5,"area":"lr"},{"id":"2412.20297","title":"FaGeL: Fabric LLMs Agent empowered Embodied Intelligence Evolution with Autonomous Human-Machine Collaboration","created":"2024-12-28","cited_by_count":2,"area":"lr"},{"id":"2510.11194","title":"Aligning Deep Implicit Preferences by Learning to Reason Defensively","created":"2025-10-13","cited_by_count":2,"area":"lr"},{"id":"2512.20812","title":"Semantic Deception: When Reasoning Models Can't Compute an Addition","created":"2025-12-23","cited_by_count":1,"area":"lr"},{"id":"2601.18760","title":"Beyond Preferences: Learning Alignment Principles Grounded in Human Reasons and Values","created":"2026-01-26","cited_by_count":1,"area":"lr"},{"id":"2605.06444","title":"SCRuB: Social Concept Reasoning under Rubric-Based Evaluation","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2410.22151","title":"Standardization Trends on Safety and Trustworthiness Technology for Advanced AI","created":"2024-10-29","cited_by_count":0,"area":"lr"},{"id":"2608.15354","title":"Incoherent by Design? On the Moral Self-Consistency of LLMs","created":"2026-08-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}