{"total":16,"rows":[{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63,"area":"alignment"},{"id":"2209.00731","title":"In conversation with Artificial Intelligence: aligning language models with human values","created":"2022-09-01","cited_by_count":62,"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":"2511.03369","title":"Silenced Biases: The Dark Side LLMs Learned to Refuse","created":"2025-11-05","cited_by_count":10,"area":"alignment"},{"id":"2406.15599","title":"Pareto-Optimal Learning from Preferences with Hidden Context","created":"2024-06-21","cited_by_count":8,"area":"alignment"},{"id":"2408.12055","title":"Aligning (Medical) LLMs for (Counterfactual) Fairness","created":"2024-08-22","cited_by_count":7,"area":"alignment"},{"id":"2510.08314","title":"To Ask or Not to Ask: Learning to Require Human Feedback","created":"2025-10-09","cited_by_count":6,"area":"alignment"},{"id":"2509.02133","title":"AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models","created":"2025-09-02","cited_by_count":2,"area":"alignment"},{"id":"2506.00152","title":"Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective","created":"2025-05-30","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":"2509.16475","title":"Towards Universal Debiasing for Language Models-based Tabular Data Generation","created":"2025-09-20","cited_by_count":1,"area":"alignment"},{"id":"2602.16438","title":"Intra-Fairness Dynamics: The Bias Spillover Effect in Targeted LLM Alignment","created":"2026-02-18","cited_by_count":1,"area":"alignment"},{"id":"2505.02433","title":"FairPO: Robust Preference Optimization for Fair Multi-Label Learning","created":"2025-05-05","cited_by_count":0,"area":"alignment"},{"id":"2603.02420","title":"Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization","created":"2026-03-02","cited_by_count":0,"area":"alignment"},{"id":"2606.01755","title":"TriAlign: Towards Universal Truth Consistency in Personalized LLM Alignment","created":"2026-06-01","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"}],"next_cursor":null}