{"total":14,"rows":[{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723,"area":"alignment"},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2312.16682","title":"Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss","created":"2023-12-27","cited_by_count":108,"area":"alignment"},{"id":"2009.06978","title":"Dialogue Response Ranking Training with Large-Scale Human Feedback Data","created":"2020-09-15","cited_by_count":68,"area":"alignment"},{"id":"2303.06135","title":"Rewarding Chatbots for Real-World Engagement with Millions of Users","created":"2023-03-10","cited_by_count":59,"area":"alignment"},{"id":"2208.03270","title":"Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback","created":"2022-08-05","cited_by_count":36,"area":"alignment"},{"id":"2208.14165","title":"Towards Boosting the Open-Domain Chatbot with Human Feedback","created":"2022-08-30","cited_by_count":11,"area":"alignment"},{"id":"2402.18950","title":"PopALM: Popularity-Aligned Language Models for Social Media Trendy Response Prediction","created":"2024-02-29","cited_by_count":8,"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":"2512.04752","title":"RLHFSpec: Breaking the Efficiency Bottleneck in RLHF Training via Adaptive Drafting","created":"2025-12-04","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":"2608.09123","title":"RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning","created":"2026-08-10","cited_by_count":2,"area":"alignment"},{"id":"2507.05660","title":"Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI","created":"2025-07-08","cited_by_count":0,"area":"alignment"},{"id":"2609.23640","title":"Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment","created":"2026-09-20","cited_by_count":0,"area":"alignment"}],"next_cursor":null}