{"total":20,"rows":[{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723,"area":"alignment"},{"id":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401,"area":"alignment"},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124,"area":"alignment"},{"id":"2410.21252","title":"LongReward: Improving Long-context Large Language Models with AI Feedback","created":"2024-10-28","cited_by_count":34,"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":"2410.06554","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","created":"2024-10-09","cited_by_count":19,"area":"alignment"},{"id":"2405.13820","title":"Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching","created":"2024-05-22","cited_by_count":17,"area":"alignment"},{"id":"2403.06754","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling","created":"2024-03-11","cited_by_count":11,"area":"alignment"},{"id":"2411.17792","title":"H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs","created":"2024-11-26","cited_by_count":11,"area":"alignment"},{"id":"2411.00722","title":"Token-level Proximal Policy Optimization for Query Generation","created":"2024-11-01","cited_by_count":7,"area":"alignment"},{"id":"2505.20081","title":"Inference-time Alignment in Continuous Space","created":"2025-05-26","cited_by_count":7,"area":"alignment"},{"id":"2504.03622","title":"Align to Structure: Aligning Large Language Models with Structural Information","created":"2025-04-04","cited_by_count":6,"area":"alignment"},{"id":"2510.17833","title":"Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage","created":"2025-10-03","cited_by_count":5,"area":"alignment"},{"id":"2503.20194","title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2505.20088","title":"Multi-Domain Explainability of Preferences","created":"2025-05-26","cited_by_count":2,"area":"alignment"},{"id":"2605.31545","title":"Preference-Aware Rubric Learning for Personalized Evaluation","created":"2026-05-29","cited_by_count":2,"area":"alignment"},{"id":"2608.02109","title":"Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression","created":"2026-08-03","cited_by_count":2,"area":"alignment"},{"id":"2412.11707","title":"Context Filtering with Reward Modeling in Question Answering","created":"2024-12-16","cited_by_count":1,"area":"alignment"},{"id":"2609.32579","title":"DimPO: Dimensionality Reduction for Attention using Preference Optimization","created":"2026-09-26","cited_by_count":0,"area":"alignment"}],"next_cursor":null}