{"total":20,"rows":[{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"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":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42,"area":"alignment"},{"id":"2008.12735","title":"Soliciting Human-in-the-Loop User Feedback for Interactive Machine Learning Reduces User Trust and Impressions of Model Accuracy","created":"2020-08-28","cited_by_count":20,"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":"2401.08672","title":"Concept Alignment","created":"2024-01-09","cited_by_count":10,"area":"alignment"},{"id":"2411.16502","title":"Interpreting Language Reward Models via Contrastive Explanations","created":"2024-11-25","cited_by_count":9,"area":"alignment"},{"id":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2203.13553","title":"Preprocessing Reward Functions for Interpretability","created":"2022-03-25","cited_by_count":7,"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":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","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":"2512.13837","title":"Explainable reinforcement learning from human feedback to improve alignment","created":"2025-12-15","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":"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":"2603.27971","title":"Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning","created":"2026-03-30","cited_by_count":0,"area":"alignment"}],"next_cursor":null}