{"total":232,"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":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724,"area":"alignment"},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100,"area":"alignment"},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912,"area":"alignment"},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"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":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625,"area":"alignment"},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562,"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":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463,"area":"alignment"},{"id":"2310.01377","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","created":"2023-10-02","cited_by_count":406,"area":"alignment"},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323,"area":"alignment"},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315,"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":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240,"area":"alignment"},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200,"area":"alignment"},{"id":"2403.19159","title":"Disentangling Length from Quality in Direct Preference Optimization","created":"2024-03-28","cited_by_count":196,"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":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187,"area":"alignment"},{"id":"2403.16950","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","created":"2024-03-25","cited_by_count":149,"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":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2309.10105","title":"Understanding Catastrophic Forgetting in Language Models via Implicit Inference","created":"2023-09-18","cited_by_count":144,"area":"alignment"},{"id":"2408.17003","title":"Safety Layers in Aligned Large Language Models: The Key to LLM Security","created":"2024-08-30","cited_by_count":134,"area":"alignment"},{"id":"2311.14455","title":"Universal Jailbreak Backdoors from Poisoned Human Feedback","created":"2023-11-24","cited_by_count":128,"area":"alignment"},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122,"area":"alignment"},{"id":"2308.03549","title":"Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue","created":"2023-08-07","cited_by_count":119,"area":"alignment"},{"id":"2310.05344","title":"SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF","created":"2023-10-09","cited_by_count":111,"area":"alignment"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2407.10490","title":"Learning Dynamics of LLM Finetuning","created":"2024-07-15","cited_by_count":95,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2406.13542","title":"Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models","created":"2024-06-19","cited_by_count":73,"area":"alignment"},{"id":"2312.15997","title":"Aligning Large Language Models with Human Preferences through Representation Engineering","created":"2023-12-26","cited_by_count":71,"area":"alignment"},{"id":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66,"area":"alignment"},{"id":"2403.18349","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","created":"2024-03-27","cited_by_count":66,"area":"alignment"},{"id":"2310.05910","title":"SALMON: Self-Alignment with Instructable Reward Models","created":"2023-10-09","cited_by_count":55,"area":"alignment"},{"id":"2204.14146","title":"Training Language Models with Language Feedback","created":"2022-04-29","cited_by_count":49,"area":"alignment"},{"id":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49,"area":"alignment"},{"id":"2405.17374","title":"Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models","created":"2024-05-27","cited_by_count":46,"area":"alignment"},{"id":"2405.19335","title":"X-VILA: Cross-Modality Alignment for Large Language Model","created":"2024-05-29","cited_by_count":46,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2503.20823","title":"Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy","created":"2025-03-26","cited_by_count":44,"area":"alignment"},{"id":"2511.07919","title":"Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison","created":"2025-11-11","cited_by_count":44,"area":"alignment"},{"id":"2405.01481","title":"NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment","created":"2024-05-02","cited_by_count":41,"area":"alignment"},{"id":"2404.05875","title":"CodecLM: Aligning Language Models with Tailored Synthetic Data","created":"2024-04-08","cited_by_count":39,"area":"alignment"},{"id":"2402.10958","title":"Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts","created":"2024-02-12","cited_by_count":36,"area":"alignment"},{"id":"2403.14221","title":"Improving the Robustness of Large Language Models via Consistency Alignment","created":"2024-03-21","cited_by_count":36,"area":"alignment"},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2311.04072","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","created":"2023-11-07","cited_by_count":35,"area":"alignment"},{"id":"2402.13659","title":"Privacy-Preserving Instructions for Aligning Large Language Models","created":"2024-02-21","cited_by_count":35,"area":"alignment"},{"id":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35,"area":"alignment"},{"id":"2406.19371","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","created":"2024-06-27","cited_by_count":34,"area":"alignment"},{"id":"2308.05696","title":"A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment","created":"2023-08-10","cited_by_count":33,"area":"alignment"},{"id":"2409.14586","title":"Backtracking Improves Generation Safety","created":"2024-09-22","cited_by_count":32,"area":"alignment"},{"id":"2410.12971","title":"Self-Pluralising Culture Alignment for Large Language Models","created":"2024-10-16","cited_by_count":31,"area":"alignment"},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2406.12935","title":"ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates","created":"2024-06-17","cited_by_count":30,"area":"alignment"},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2406.04412","title":"Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment","created":"2024-06-06","cited_by_count":27,"area":"alignment"},{"id":"2401.06785","title":"Human-Instruction-Free LLM Self-Alignment with Limited Samples","created":"2024-01-06","cited_by_count":25,"area":"alignment"},{"id":"2405.05008","title":"ADELIE: Aligning Large Language Models on Information Extraction","created":"2024-05-08","cited_by_count":24,"area":"alignment"},{"id":"2502.13922","title":"LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization","created":"2025-02-19","cited_by_count":24,"area":"alignment"},{"id":"2308.15812","title":"Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models","created":"2023-08-30","cited_by_count":23,"area":"alignment"},{"id":"2312.15907","title":"Align on the Fly: Adapting Chatbot Behavior to Established Norms","created":"2023-12-26","cited_by_count":23,"area":"alignment"},{"id":"2406.08725","title":"RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs","created":"2024-06-13","cited_by_count":23,"area":"alignment"},{"id":"2406.11431","title":"Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization","created":"2024-06-17","cited_by_count":23,"area":"alignment"},{"id":"2410.18640","title":"Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model","created":"2024-10-24","cited_by_count":22,"area":"alignment"},{"id":"2406.13173","title":"Biomedical Visual Instruction Tuning with Clinician Preference Alignment","created":"2024-06-19","cited_by_count":21,"area":"alignment"},{"id":"2310.11732","title":"Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting","created":"2023-10-18","cited_by_count":20,"area":"alignment"},{"id":"2410.17875","title":"Understanding Layer Significance in LLM Alignment","created":"2024-10-23","cited_by_count":19,"area":"alignment"},{"id":"2405.13068","title":"Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment","created":"2024-05-20","cited_by_count":18,"area":"alignment"},{"id":"2405.19744","title":"X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions","created":"2024-05-30","cited_by_count":18,"area":"alignment"},{"id":"2406.10630","title":"Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models","created":"2024-06-15","cited_by_count":18,"area":"alignment"},{"id":"2502.09723","title":"QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language","created":"2025-02-13","cited_by_count":18,"area":"alignment"},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18,"area":"alignment"},{"id":"2506.17368","title":"SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification","created":"2025-06-20","cited_by_count":18,"area":"alignment"},{"id":"2305.14718","title":"Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models","created":"2023-05-24","cited_by_count":17,"area":"alignment"},{"id":"2406.09920","title":"Knowledge Editing in Language Models via Adapted Direct Preference Optimization","created":"2024-06-14","cited_by_count":17,"area":"alignment"},{"id":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"id":"2402.12219","title":"Reformatted Alignment","created":"2024-02-19","cited_by_count":15,"area":"alignment"},{"id":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15,"area":"alignment"},{"id":"2507.14987","title":"AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning","created":"2025-07-20","cited_by_count":15,"area":"alignment"},{"id":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2308.12050","title":"Aligning Language Models with Offline Learning from Human Feedback","created":"2023-08-23","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":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2505.18588","title":"Safety Alignment via Constrained Knowledge Unlearning","created":"2025-05-24","cited_by_count":14,"area":"alignment"},{"id":"2506.14681","title":"Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality","created":"2025-06-17","cited_by_count":14,"area":"alignment"},{"id":"2210.07652","title":"Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values","created":"2022-10-14","cited_by_count":13,"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":"2403.10088","title":"Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF","created":"2024-03-15","cited_by_count":13,"area":"alignment"},{"id":"2404.03862","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","created":"2024-04-05","cited_by_count":13,"area":"alignment"},{"id":"2507.21182","title":"SDD: Self-Degraded Defense against Malicious Fine-tuning","created":"2025-07-27","cited_by_count":13,"area":"alignment"}],"next_cursor":"100"}