{"total":23,"rows":[{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2402.15754","title":"HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition","created":"2024-02-24","cited_by_count":33,"area":"alignment"},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2505.20417","title":"SCAR: Shapley Credit Assignment for More Efficient RLHF","created":"2025-05-26","cited_by_count":16,"area":"alignment"},{"id":"2311.10947","title":"RecExplainer: Aligning Large Language Models for Explaining Recommendation Models","created":"2023-11-18","cited_by_count":14,"area":"alignment"},{"id":"2410.07304","title":"The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making","created":"2024-10-09","cited_by_count":12,"area":"alignment"},{"id":"2506.08712","title":"ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization","created":"2025-06-10","cited_by_count":10,"area":"alignment"},{"id":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2506.07523","title":"Aligning What LLMs Do and Say: Towards Self-Consistent Explanations","created":"2025-06-09","cited_by_count":4,"area":"alignment"},{"id":"2307.03887","title":"Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining","created":"2023-07-08","cited_by_count":3,"area":"alignment"},{"id":"2504.16272","title":"Learning Explainable Dense Reward Shapes via Bayesian Optimization","created":"2025-04-22","cited_by_count":2,"area":"alignment"},{"id":"2403.02514","title":"The Autonomy-Alignment Problem in Open-Ended Learning Robots: Formalising the Purpose Framework","created":"2024-03-04","cited_by_count":1,"area":"alignment"},{"id":"2604.27401","title":"Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs","created":"2026-04-30","cited_by_count":1,"area":"alignment"},{"id":"2402.15826","title":"Reward Design for Justifiable Sequential Decision-Making","created":"2024-02-24","cited_by_count":0,"area":"alignment"},{"id":"2505.15626","title":"Direct Preference Optimization for Adaptive Concept-based Explanations","created":"2025-05-21","cited_by_count":0,"area":"alignment"},{"id":"2506.04063","title":"Crowd-SFT: Crowdsourcing for LLM Alignment","created":"2025-06-04","cited_by_count":0,"area":"alignment"},{"id":"2512.04302","title":"Towards better dense rewards in Reinforcement Learning Applications","created":"2025-12-03","cited_by_count":0,"area":"alignment"},{"id":"2601.11379","title":"Evaluating LLM Behavior in Hiring: Implicit Weights, Fairness Across Groups, and Alignment with Human Preferences","created":"2026-01-16","cited_by_count":0,"area":"alignment"},{"id":"2602.02304","title":"Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2602.05056","title":"Grounded but Misleading: Evaluating Semantic Alignment in AI-Generated Security Explanations","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2606.24622","title":"Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback","created":"2026-06-23","cited_by_count":0,"area":"alignment"},{"id":"2607.24484","title":"What do Reward Models Memorize?","created":"2026-07-27","cited_by_count":0,"area":"alignment"},{"id":"2608.15530","title":"Why Summaries Turn Neutral: Policy Attribution for Sentiment Drift in Reinforcement Learning from Human Feedback","created":"2026-08-16","cited_by_count":0,"area":"alignment"}],"next_cursor":null}