{"total":17,"rows":[{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"id":"2303.16755","title":"Training Language Models with Language Feedback at Scale","created":"2023-03-28","cited_by_count":128,"area":"alignment"},{"id":"2406.11801","title":"Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations","created":"2024-06-17","cited_by_count":32,"area":"alignment"},{"id":"2406.12935","title":"ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates","created":"2024-06-17","cited_by_count":30,"area":"alignment"},{"id":"2310.03304","title":"Learning Personalized Alignment for Evaluating Open-ended Text Generation","created":"2023-10-05","cited_by_count":29,"area":"alignment"},{"id":"2406.11370","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","created":"2024-06-17","cited_by_count":25,"area":"alignment"},{"id":"2503.11751","title":"reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs","created":"2025-03-14","cited_by_count":25,"area":"alignment"},{"id":"2408.16482","title":"Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning","created":"2024-08-29","cited_by_count":19,"area":"alignment"},{"id":"2402.14688","title":"Q-Probe: A Lightweight Approach to Reward Maximization for Language Models","created":"2024-02-22","cited_by_count":15,"area":"alignment"},{"id":"2210.07652","title":"Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values","created":"2022-10-14","cited_by_count":13,"area":"alignment"},{"id":"2305.02531","title":"Can LLMs Capture Human Preferences?","created":"2023-05-04","cited_by_count":6,"area":"alignment"},{"id":"2502.01925","title":"PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling","created":"2025-02-04","cited_by_count":6,"area":"alignment"},{"id":"2501.17117","title":"Histoires Morales: A French Dataset for Assessing Moral Alignment","created":"2025-01-28","cited_by_count":4,"area":"alignment"},{"id":"2603.19311","title":"PrefPO: Pairwise Preference Prompt Optimization","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2502.19463","title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","created":"2025-02-26","cited_by_count":1,"area":"alignment"},{"id":"2406.01070","title":"Guiding ChatGPT to Generate Salient Domain Summaries","created":"2024-06-03","cited_by_count":0,"area":"alignment"},{"id":"2406.14208","title":"SeCoKD: Aligning Large Language Models for In-Context Learning with Fewer Shots","created":"2024-06-20","cited_by_count":0,"area":"alignment"}],"next_cursor":null}