{"total":28,"rows":[{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262,"area":"alignment"},{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185,"area":"alignment"},{"id":"2402.13231","title":"Investigating Cultural Alignment of Large Language Models","created":"2024-02-20","cited_by_count":143,"area":"alignment"},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55,"area":"alignment"},{"id":"2402.10958","title":"Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts","created":"2024-02-12","cited_by_count":36,"area":"alignment"},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35,"area":"alignment"},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2202.09662","title":"Reward Modeling for Mitigating Toxicity in Transformer-based Language Models","created":"2022-02-19","cited_by_count":18,"area":"alignment"},{"id":"2210.07792","title":"Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning","created":"2022-10-14","cited_by_count":14,"area":"alignment"},{"id":"2402.00402","title":"Investigating Bias Representations in Llama 2 Chat via Activation Steering","created":"2024-02-01","cited_by_count":14,"area":"alignment"},{"id":"2512.11391","title":"Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization","created":"2025-12-12","cited_by_count":11,"area":"alignment"},{"id":"2409.00787","title":"The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs","created":"2024-09-01","cited_by_count":10,"area":"alignment"},{"id":"2511.03369","title":"Silenced Biases: The Dark Side LLMs Learned to Refuse","created":"2025-11-05","cited_by_count":10,"area":"alignment"},{"id":"2405.20830","title":"Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2409.18618","title":"Model-based Preference Optimization in Abstractive Summarization without Human Feedback","created":"2024-09-27","cited_by_count":7,"area":"alignment"},{"id":"2410.03818","title":"Large Language Models can be Strong Self-Detoxifiers","created":"2024-10-04","cited_by_count":7,"area":"alignment"},{"id":"2506.06404","title":"Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights","created":"2025-06-06","cited_by_count":7,"area":"alignment"},{"id":"2211.05750","title":"Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control","created":"2022-11-10","cited_by_count":6,"area":"alignment"},{"id":"2411.03700","title":"The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models","created":"2024-11-06","cited_by_count":5,"area":"alignment"},{"id":"2503.10093","title":"Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling","created":"2025-03-13","cited_by_count":4,"area":"alignment"},{"id":"2407.04615","title":"On the Low-Rank Parametrization of Reward Models for Controlled Language Generation","created":"2024-07-05","cited_by_count":3,"area":"alignment"},{"id":"2602.23391","title":"Detoxifying LLMs via Representation Erasure-Based Preference Optimization","created":"2026-02-24","cited_by_count":1,"area":"alignment"},{"id":"2607.07023","title":"Online Data Selection Is Implicit Alignment","created":"2026-07-08","cited_by_count":1,"area":"alignment"},{"id":"2510.22084","title":"Compositional Bias Control in Large Language Models: Preference Learning Fails, Supervision Succeeds","created":"2025-10-24","cited_by_count":0,"area":"alignment"},{"id":"2604.04410","title":"Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment","created":"2026-04-06","cited_by_count":0,"area":"alignment"},{"id":"2608.22490","title":"Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across Languages","created":"2026-08-23","cited_by_count":0,"area":"alignment"}],"next_cursor":null}