{"total":53,"rows":[{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860,"area":"alignment"},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"id":"2305.03047","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision","created":"2023-05-04","cited_by_count":318,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240,"area":"alignment"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173,"area":"alignment"},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2401.11206","title":"InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance","created":"2024-01-20","cited_by_count":83,"area":"alignment"},{"id":"2405.09719","title":"Spectral Editing of Activations for Large Language Model Alignment","created":"2024-05-15","cited_by_count":56,"area":"alignment"},{"id":"2402.05699","title":"Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation","created":"2024-02-08","cited_by_count":46,"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":"2311.06899","title":"Flames: Benchmarking Value Alignment of LLMs in Chinese","created":"2023-11-12","cited_by_count":37,"area":"alignment"},{"id":"2310.10477","title":"Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis","created":"2023-10-16","cited_by_count":35,"area":"alignment"},{"id":"2409.15268","title":"Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking","created":"2024-09-23","cited_by_count":35,"area":"alignment"},{"id":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33,"area":"alignment"},{"id":"2408.15313","title":"Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models","created":"2024-08-27","cited_by_count":27,"area":"alignment"},{"id":"2404.10160","title":"Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs","created":"2024-04-15","cited_by_count":22,"area":"alignment"},{"id":"2501.14940","title":"CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models","created":"2025-01-24","cited_by_count":20,"area":"alignment"},{"id":"2503.18991","title":"Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment","created":"2025-03-23","cited_by_count":20,"area":"alignment"},{"id":"2402.17358","title":"SoFA: Shielded On-the-fly Alignment via Priority Rule Following","created":"2024-02-27","cited_by_count":18,"area":"alignment"},{"id":"2406.13925","title":"GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models","created":"2024-06-20","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":"2409.04340","title":"AGR: Age Group fairness Reward for Bias Mitigation in LLMs","created":"2024-09-06","cited_by_count":12,"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":"2511.14476","title":"Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior","created":"2025-11-18","cited_by_count":9,"area":"alignment"},{"id":"2502.00814","title":"Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2508.05553","title":"Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMs","created":"2025-08-07","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":"2408.00307","title":"ABC Align: Large Language Model Alignment for Safety & Accuracy","created":"2024-08-01","cited_by_count":4,"area":"alignment"},{"id":"2602.20042","title":"AI Alignment Breaks at the Edge","created":"2026-02-23","cited_by_count":4,"area":"alignment"},{"id":"2401.09566","title":"Aligning Large Language Models with Counterfactual DPO","created":"2024-01-17","cited_by_count":3,"area":"alignment"},{"id":"2506.01495","title":"C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2509.13869","title":"Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs","created":"2025-09-17","cited_by_count":3,"area":"alignment"},{"id":"2504.12553","title":"ELAB: Extensive LLM Alignment Benchmark in Persian Language","created":"2025-04-17","cited_by_count":2,"area":"alignment"},{"id":"2604.02174","title":"Quantifying Self-Preservation Bias in Large Language Models","created":"2026-04-02","cited_by_count":2,"area":"alignment"},{"id":"2510.06391","title":"Reward Model Perspectives: Whose Opinions Do Reward Models Reward?","created":"2025-10-07","cited_by_count":1,"area":"alignment"},{"id":"2602.07799","title":"Fairness Aware Reward Optimization","created":"2026-02-08","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":"2605.05003","title":"Misaligned by Reward: Socially Undesirable Preferences in LLMs","created":"2026-05-06","cited_by_count":1,"area":"alignment"},{"id":"2512.10601","title":"Multi-Objective Reward and Preference Optimization: Theory and Algorithms","created":"2025-12-11","cited_by_count":0,"area":"alignment"},{"id":"2601.04389","title":"Safety Is Not Universal: The Selective Safety Trap in LLM Alignment","created":"2026-01-07","cited_by_count":0,"area":"alignment"},{"id":"2603.06264","title":"Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion","created":"2026-03-06","cited_by_count":0,"area":"alignment"},{"id":"2604.17691","title":"SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models","created":"2026-04-20","cited_by_count":0,"area":"alignment"},{"id":"2605.28722","title":"Multi-Adapter Representation Interventions via Energy Calibration","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2607.22305","title":"A Roadmap to Impactful Pluralistic Alignment Research","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2608.03532","title":"Cross-Lingual Bias in Large Language Models: A Comparative Analysis of English and Swahili","created":"2026-08-04","cited_by_count":0,"area":"alignment"},{"id":"2608.09551","title":"Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.18096","title":"MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators","created":"2026-06-08","cited_by_count":0,"area":"alignment"},{"id":"2608.20554","title":"aiXamine: Unified Black-Box Evaluation of Cross-Dimensional Trade-offs in LLM Safety, Security, and Privacy","created":"2026-08-20","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}