{"total":19,"rows":[{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"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":"2312.07401","title":"On Diversified Preferences of Large Language Model Alignment","created":"2023-12-12","cited_by_count":26,"area":"alignment"},{"id":"2406.10630","title":"Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models","created":"2024-06-15","cited_by_count":18,"area":"alignment"},{"id":"2503.09925","title":"PluralLLM: Pluralistic Alignment in LLMs via Federated Learning","created":"2025-03-13","cited_by_count":14,"area":"alignment"},{"id":"2504.16438","title":"POPri: Private Federated Learning using Preference-Optimized Synthetic Data","created":"2025-04-23","cited_by_count":14,"area":"alignment"},{"id":"2407.03038","title":"Towards Federated RLHF with Aggregated Client Preference for LLMs","created":"2024-07-03","cited_by_count":13,"area":"alignment"},{"id":"2412.15538","title":"FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF","created":"2024-12-20","cited_by_count":12,"area":"alignment"},{"id":"2506.00569","title":"AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs","created":"2025-05-31","cited_by_count":8,"area":"alignment"},{"id":"2310.15477","title":"CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model","created":"2023-10-24","cited_by_count":5,"area":"alignment"},{"id":"2502.14187","title":"Federated Fine-Tuning of Large Language Models: Kahneman-Tversky vs. Direct Preference Optimization","created":"2025-02-20","cited_by_count":4,"area":"alignment"},{"id":"2502.16691","title":"Responsible Federated LLMs via Safety Filtering and Constitutional AI","created":"2025-02-23","cited_by_count":1,"area":"alignment"},{"id":"2508.06783","title":"PROPS: Progressively Private Self-alignment of Large Language Models","created":"2025-08-09","cited_by_count":1,"area":"alignment"},{"id":"2511.16992","title":"FIRM: Federated In-client Regularized Multi-objective Alignment for Large Language Models","created":"2025-11-21","cited_by_count":1,"area":"alignment"},{"id":"2604.06833","title":"FedDetox: Robust Federated SLM Alignment via On-Device Data Sanitization","created":"2026-04-08","cited_by_count":0,"area":"alignment"},{"id":"2604.17747","title":"Efficient Federated RLHF via Zeroth-Order Policy Optimization","created":"2026-04-20","cited_by_count":0,"area":"alignment"},{"id":"2605.30873","title":"Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences","created":"2026-05-29","cited_by_count":0,"area":"alignment"}],"next_cursor":null}