{"total":18,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"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":"2401.03129","title":"Examining Forgetting in Continual Pre-training of Aligned Large Language Models","created":"2024-01-06","cited_by_count":18,"area":"alignment"},{"id":"2407.13928","title":"BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization","created":"2024-07-18","cited_by_count":18,"area":"alignment"},{"id":"2506.00253","title":"Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race","created":"2025-05-30","cited_by_count":15,"area":"alignment"},{"id":"2411.11937","title":"Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets","created":"2024-11-18","cited_by_count":11,"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":"2504.12911","title":"Benchmarking Multi-National Value Alignment for Large Language Models","created":"2025-04-17","cited_by_count":7,"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":"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":"2507.14202","title":"PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training","created":"2025-07-14","cited_by_count":1,"area":"alignment"},{"id":"2604.02669","title":"Redirected, Not Removed: Task-Dependent Stereotyping Reveals the Limits of LLM Alignments","created":"2026-04-03","cited_by_count":1,"area":"alignment"},{"id":"2606.04807","title":"BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization","created":"2026-06-03","cited_by_count":1,"area":"alignment"},{"id":"2602.04294","title":"How Few-shot Demonstrations Affect Prompt-based Defenses Against LLM Jailbreak Attacks","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2604.24429","title":"A Multi-Dimensional Audit of Politically Aligned Large Language Models","created":"2026-04-27","cited_by_count":0,"area":"alignment"},{"id":"2609.14860","title":"One Example Is Enough to Pass Fairness Benchmarks: Rethinking Fairness Evaluation for Aligned LLMs","created":"2026-09-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}