{"total":34,"rows":[{"id":"2502.09650","title":"Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples","created":"2025-02-11","cited_by_count":37,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2501.03884","title":"AlphaPO: Reward Shape Matters for LLM Alignment","created":"2025-01-07","cited_by_count":14,"area":"alignment"},{"id":"2505.05465","title":"ComPO: Preference Alignment via Comparison Oracles","created":"2025-05-08","cited_by_count":13,"area":"alignment"},{"id":"2505.19770","title":"Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO","created":"2025-05-26","cited_by_count":10,"area":"alignment"},{"id":"2602.04896","title":"Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models","created":"2026-02-03","cited_by_count":8,"area":"alignment"},{"id":"2602.18037","title":"Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards","created":"2026-02-20","cited_by_count":8,"area":"alignment"},{"id":"2505.02363","title":"SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning","created":"2025-05-05","cited_by_count":6,"area":"alignment"},{"id":"2507.07981","title":"Why is Your Language Model a Poor Implicit Reward Model?","created":"2025-07-10","cited_by_count":6,"area":"alignment"},{"id":"2412.17696","title":"Understanding the Logic of Direct Preference Alignment through Logic","created":"2024-12-23","cited_by_count":5,"area":"alignment"},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"},{"id":"2505.12435","title":"SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment","created":"2025-05-18","cited_by_count":3,"area":"alignment"},{"id":"2510.20413","title":"Why DPO is a Misspecified Estimator and How to Fix It","created":"2025-10-23","cited_by_count":3,"area":"alignment"},{"id":"2502.17507","title":"C2-DPO: Constrained Controlled Direct Preference Optimization","created":"2025-02-22","cited_by_count":2,"area":"alignment"},{"id":"2602.00603","title":"Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2602.00954","title":"Small-Margin Preferences Still Matter-If You Train Them Right","created":"2026-02-01","cited_by_count":2,"area":"alignment"},{"id":"2604.18239","title":"Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner","created":"2026-04-20","cited_by_count":2,"area":"alignment"},{"id":"2502.05773","title":"PIPA: Preference Alignment as Prior-Informed Statistical Estimation","created":"2025-02-09","cited_by_count":1,"area":"alignment"},{"id":"2505.19964","title":"The Limits of Preference Data for Post-Training","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2505.23761","title":"Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2506.05260","title":"LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs","created":"2025-06-05","cited_by_count":1,"area":"alignment"},{"id":"2603.18258","title":"Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization","created":"2026-03-18","cited_by_count":1,"area":"alignment"},{"id":"2604.08723","title":"Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?","created":"2026-04-09","cited_by_count":1,"area":"alignment"},{"id":"2605.02626","title":"Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models","created":"2026-05-04","cited_by_count":1,"area":"alignment"},{"id":"2607.16240","title":"Normalized Rewards for Preference Optimization","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2506.08998","title":"On Monotonicity in AI Alignment","created":"2025-06-10","cited_by_count":0,"area":"alignment"},{"id":"2507.20133","title":"Sem-DPO: Mitigating Semantic Inconsistency in Preference Optimization for Prompt Engineering","created":"2025-07-27","cited_by_count":0,"area":"alignment"},{"id":"2602.06788","title":"Displacement-Resistant Extensions of DPO with Nonconvex $f$-Divergences","created":"2026-02-06","cited_by_count":0,"area":"alignment"},{"id":"2605.23961","title":"Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2607.13430","title":"Exploring Post-Training Alignment of Small Language Models for Biomedical Data-to-Text Generation: A Case Study of Medication Leaflet","created":"2026-07-15","cited_by_count":0,"area":"alignment"},{"id":"2609.08634","title":"Suan: Rectifying Direct Preference Safety Alignment in Large Language Models","created":"2026-09-08","cited_by_count":0,"area":"alignment"},{"id":"2609.32445","title":"Masking Frequent Tokens Sharpens Direct Preference Optimization","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2610.01511","title":"GAW-PO: Preference Optimization with Gradient-Aligned Token Weights","created":"2026-10-01","cited_by_count":0,"area":"alignment"}],"next_cursor":null}