{"total":17,"rows":[{"id":"2310.05782","title":"Aligning Language Models with Human Preferences via a Bayesian Approach","created":"2023-10-09","cited_by_count":27,"area":"alignment"},{"id":"2505.16610","title":"From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignment","created":"2025-05-22","cited_by_count":9,"area":"alignment"},{"id":"2401.05928","title":"Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback","created":"2024-01-11","cited_by_count":5,"area":"alignment"},{"id":"2505.16995","title":"DecoupledESC: Enhancing Emotional Support Generation via Strategy-Response Decoupled Preference Optimization","created":"2025-05-22","cited_by_count":5,"area":"alignment"},{"id":"2508.12935","title":"Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewards","created":"2025-08-18","cited_by_count":5,"area":"alignment"},{"id":"2406.19071","title":"EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization","created":"2024-06-27","cited_by_count":4,"area":"alignment"},{"id":"2503.00018","title":"Eeyore: Realistic Depression Simulation via Supervised and Preference Optimization","created":"2025-02-21","cited_by_count":3,"area":"alignment"},{"id":"2411.01245","title":"PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment","created":"2024-11-02","cited_by_count":1,"area":"alignment"},{"id":"2506.21497","title":"Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments","created":"2025-06-26","cited_by_count":1,"area":"alignment"},{"id":"2511.05407","title":"Minority-Aware Satisfaction Estimation in Dialogue Systems via Preference-Adaptive Reinforcement Learning","created":"2025-11-07","cited_by_count":1,"area":"alignment"},{"id":"2603.15434","title":"Listening to the Echo: User-Reaction Aware Policy Optimization via Scalar-Verbal Hybrid Reinforcement Learning","created":"2026-03-16","cited_by_count":1,"area":"alignment"},{"id":"2509.12661","title":"Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations","created":"2025-09-16","cited_by_count":0,"area":"alignment"},{"id":"2608.14828","title":"MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment","created":"2026-08-14","cited_by_count":0,"area":"alignment"},{"id":"2608.21969","title":"ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents","created":"2026-08-22","cited_by_count":0,"area":"alignment"},{"id":"2608.29326","title":"StageWell: A Process-Aligned Chinese Corpus for Positive-Psychology Support Dialogue","created":"2026-08-29","cited_by_count":0,"area":"alignment"},{"id":"2609.00921","title":"VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferences","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.21075","title":"Aligning with Lived Experience: Heterogeneous Benefits of Fine Tuning in Mental Health Support Generation","created":"2026-09-17","cited_by_count":0,"area":"alignment"}],"next_cursor":null}