{"total":47,"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":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2307.16039","title":"Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback","created":"2023-07-29","cited_by_count":190,"area":"alignment"},{"id":"2211.15006","title":"Fine-tuning language models to find agreement among humans with diverse preferences","created":"2022-11-28","cited_by_count":189,"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":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87,"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":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2209.00731","title":"In conversation with Artificial Intelligence: aligning language models with human values","created":"2022-09-01","cited_by_count":62,"area":"alignment"},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55,"area":"alignment"},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2310.19677","title":"MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks","created":"2023-10-30","cited_by_count":44,"area":"alignment"},{"id":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33,"area":"alignment"},{"id":"2405.17713","title":"AI Alignment with Changing and Influenceable Reward Functions","created":"2024-05-28","cited_by_count":33,"area":"alignment"},{"id":"2404.00934","title":"ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback","created":"2024-04-01","cited_by_count":25,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2403.07708","title":"Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards","created":"2024-03-12","cited_by_count":23,"area":"alignment"},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2507.05619","title":"Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests","created":"2025-07-08","cited_by_count":19,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2303.02891","title":"Perspectives on the Social Impacts of Reinforcement Learning with Human Feedback","created":"2023-03-06","cited_by_count":15,"area":"alignment"},{"id":"2410.05328","title":"Reward Learning From Preference With Ties","created":"2024-10-05","cited_by_count":14,"area":"alignment"},{"id":"2312.11819","title":"An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training","created":"2023-12-19","cited_by_count":13,"area":"alignment"},{"id":"2405.13516","title":"LIRE: listwise reward enhancement for preference alignment","created":"2024-05-22","cited_by_count":11,"area":"alignment"},{"id":"2406.07295","title":"Multi-objective Reinforcement learning from AI Feedback","created":"2024-06-11","cited_by_count":10,"area":"alignment"},{"id":"2507.20333","title":"The Blessing and Curse of Dimensionality in Safety Alignment","created":"2025-07-27","cited_by_count":10,"area":"alignment"},{"id":"2404.18870","title":"More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness","created":"2024-04-29","cited_by_count":9,"area":"alignment"},{"id":"2602.22554","title":"Multilingual Safety Alignment Via Sparse Weight Editing","created":"2026-02-26","cited_by_count":6,"area":"alignment"},{"id":"2508.19697","title":"Safety Alignment Should Be Made More Than Just A Few Attention Heads","created":"2025-08-27","cited_by_count":5,"area":"alignment"},{"id":"2308.06385","title":"ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF","created":"2023-08-11","cited_by_count":4,"area":"alignment"},{"id":"2406.03642","title":"Is Free Self-Alignment Possible?","created":"2024-06-05","cited_by_count":4,"area":"alignment"},{"id":"2411.01798","title":"SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF","created":"2024-11-04","cited_by_count":4,"area":"alignment"},{"id":"2507.15328","title":"On the Inevitability of Left-Leaning Political Bias in Aligned Language Models","created":"2025-07-21","cited_by_count":4,"area":"alignment"},{"id":"2501.14294","title":"Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes","created":"2025-01-24","cited_by_count":3,"area":"alignment"},{"id":"2601.19231","title":"LLMs Can Unlearn Refusal with Only 1,000 Benign Samples","created":"2026-01-27","cited_by_count":3,"area":"alignment"},{"id":"2410.00508","title":"FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization","created":"2024-10-01","cited_by_count":2,"area":"alignment"},{"id":"2507.00239","title":"Linearly Decoding Refused Knowledge in Aligned Language Models","created":"2025-06-30","cited_by_count":2,"area":"alignment"},{"id":"2510.06096","title":"The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives","created":"2025-10-07","cited_by_count":2,"area":"alignment"},{"id":"2606.21550","title":"AI Alignment From Social Choice Perspectives","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"id":"2502.19463","title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","created":"2025-02-26","cited_by_count":1,"area":"alignment"},{"id":"2511.21737","title":"Polarity-Aware Probing for Quantifying Latent Alignment in Language Models","created":"2025-11-21","cited_by_count":1,"area":"alignment"},{"id":"2509.00091","title":"Ensemble Debates with Local Large Language Models for AI Alignment","created":"2025-08-27","cited_by_count":0,"area":"alignment"},{"id":"2509.07642","title":"Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignment","created":"2025-09-09","cited_by_count":0,"area":"alignment"},{"id":"2602.08377","title":"Reinforcement Learning with Backtracking Feedback","created":"2026-02-09","cited_by_count":0,"area":"alignment"},{"id":"2604.01837","title":"PLOT: Enhancing Preference Learning via Optimal Transport","created":"2026-04-02","cited_by_count":0,"area":"alignment"}],"next_cursor":null}