{"total":26,"rows":[{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297,"area":"alignment"},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171,"area":"alignment"},{"id":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78,"area":"alignment"},{"id":"2402.18091","title":"Polos: Multimodal Metric Learning from Human Feedback for Image Captioning","created":"2024-02-28","cited_by_count":46,"area":"alignment"},{"id":"2410.10624","title":"SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition","created":"2024-10-14","cited_by_count":38,"area":"alignment"},{"id":"2305.01918","title":"Improving Contrastive Learning of Sentence Embeddings from AI Feedback","created":"2023-05-03","cited_by_count":29,"area":"alignment"},{"id":"2309.16155","title":"The Trickle-down Impact of Reward (In-)consistency on RLHF","created":"2023-09-28","cited_by_count":29,"area":"alignment"},{"id":"2410.19198","title":"MAP: Multi-Human-Value Alignment Palette","created":"2024-10-24","cited_by_count":20,"area":"alignment"},{"id":"2206.04105","title":"Words are all you need? Language as an approximation for human similarity judgments","created":"2022-06-08","cited_by_count":18,"area":"alignment"},{"id":"2309.10202","title":"Stabilizing RLHF through Advantage Model and Selective Rehearsal","created":"2023-09-18","cited_by_count":14,"area":"alignment"},{"id":"2405.09223","title":"Word Alignment as Preference for Machine Translation","created":"2024-05-15","cited_by_count":14,"area":"alignment"},{"id":"2403.03419","title":"Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization","created":"2024-03-06","cited_by_count":11,"area":"alignment"},{"id":"2504.10208","title":"From Prompting to Alignment: A Generative Framework for Query Recommendation","created":"2025-04-14","cited_by_count":7,"area":"alignment"},{"id":"2406.07971","title":"It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF","created":"2024-06-12","cited_by_count":5,"area":"alignment"},{"id":"2306.13588","title":"System-Level Natural Language Feedback","created":"2023-06-23","cited_by_count":4,"area":"alignment"},{"id":"2403.16649","title":"CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment","created":"2024-03-25","cited_by_count":3,"area":"alignment"},{"id":"2606.21795","title":"Discretizing Reward Models","created":"2026-06-19","cited_by_count":3,"area":"alignment"},{"id":"2507.08020","title":"Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation","created":"2025-07-08","cited_by_count":2,"area":"alignment"},{"id":"2512.11838","title":"D-STEER - Preference Alignment Techniques Learn to Behave, not to Believe -- Beneath the Surface, DPO as Steering Vector Perturbation in Activation Space","created":"2025-12-03","cited_by_count":2,"area":"alignment"},{"id":"2502.12375","title":"UltraGen: Extremely Fine-grained Controllable Generation via Attribute Reconstruction and Global Preference Optimization","created":"2025-02-17","cited_by_count":1,"area":"alignment"},{"id":"2505.09039","title":"Atomic Consistency Preference Optimization for Long-Form Question Answering","created":"2025-05-14","cited_by_count":1,"area":"alignment"},{"id":"2601.05075","title":"SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment","created":"2026-01-08","cited_by_count":1,"area":"alignment"},{"id":"2603.29123","title":"Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2503.10723","title":"RankPO: Preference Optimization for Job-Talent Matching","created":"2025-03-13","cited_by_count":0,"area":"alignment"},{"id":"2508.02063","title":"TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs","created":"2025-08-04","cited_by_count":0,"area":"alignment"},{"id":"2602.17658","title":"MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling","created":"2026-02-19","cited_by_count":0,"area":"alignment"}],"next_cursor":null}