{"total":31,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971,"area":"alignment"},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100,"area":"alignment"},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748,"area":"alignment"},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"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":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229,"area":"alignment"},{"id":"2309.14348","title":"Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM","created":"2023-09-18","cited_by_count":192,"area":"alignment"},{"id":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148,"area":"alignment"},{"id":"2310.15140","title":"AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models","created":"2023-10-23","cited_by_count":111,"area":"alignment"},{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107,"area":"alignment"},{"id":"2310.09520","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","created":"2023-10-14","cited_by_count":79,"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":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57,"area":"alignment"},{"id":"2310.04799","title":"Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages","created":"2023-10-07","cited_by_count":54,"area":"alignment"},{"id":"2510.05024","title":"Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment","created":"2025-10-06","cited_by_count":43,"area":"alignment"},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35,"area":"alignment"},{"id":"2401.07382","title":"Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation","created":"2024-01-14","cited_by_count":22,"area":"alignment"},{"id":"2408.15625","title":"CBF-LLM: Safe Control for LLM Alignment","created":"2024-08-28","cited_by_count":9,"area":"alignment"},{"id":"2410.03818","title":"Large Language Models can be Strong Self-Detoxifiers","created":"2024-10-04","cited_by_count":7,"area":"alignment"},{"id":"2508.14904","title":"Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training","created":"2025-08-12","cited_by_count":7,"area":"alignment"},{"id":"2603.00025","title":"TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation","created":"2026-02-03","cited_by_count":7,"area":"alignment"},{"id":"2211.05750","title":"Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control","created":"2022-11-10","cited_by_count":6,"area":"alignment"},{"id":"2407.16970","title":"Towards Aligning Language Models with Textual Feedback","created":"2024-07-24","cited_by_count":5,"area":"alignment"},{"id":"2503.20194","title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2407.04615","title":"On the Low-Rank Parametrization of Reward Models for Controlled Language Generation","created":"2024-07-05","cited_by_count":3,"area":"alignment"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2505.13448","title":"CIE: Controlling Language Model Text Generations Using Continuous Signals","created":"2025-05-19","cited_by_count":1,"area":"alignment"},{"id":"2511.03121","title":"Control Barrier Function for Aligning Large Language Models","created":"2025-11-05","cited_by_count":0,"area":"alignment"},{"id":"2606.13227","title":"PolyAlign: Conditional Human-Distribution Alignment","created":"2026-06-11","cited_by_count":0,"area":"alignment"},{"id":"2609.07808","title":"You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs","created":"2026-09-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}