{"total":174,"rows":[{"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":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723,"area":"alignment"},{"id":"2305.03047","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision","created":"2023-05-04","cited_by_count":318,"area":"alignment"},{"id":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244,"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":"2307.16039","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":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2303.09618","title":"HIVE: Harnessing Human Feedback for Instructional Visual Editing","created":"2023-03-16","cited_by_count":173,"area":"alignment"},{"id":"2304.11082","title":"Fundamental Limitations of Alignment in Large Language Models","created":"2023-04-19","cited_by_count":155,"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":"2406.10216","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","created":"2024-06-14","cited_by_count":142,"area":"alignment"},{"id":"2402.11746","title":"Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic","created":"2024-02-19","cited_by_count":112,"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":"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":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72,"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":"2310.05910","title":"SALMON: Self-Alignment with Instructable Reward Models","created":"2023-10-09","cited_by_count":55,"area":"alignment"},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2306.02231","title":"Fine-Tuning Language Models with Advantage-Induced Policy Alignment","created":"2023-06-04","cited_by_count":48,"area":"alignment"},{"id":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"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":"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":"2311.06025","title":"ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences","created":"2023-11-10","cited_by_count":43,"area":"alignment"},{"id":"2402.12366","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","created":"2024-02-19","cited_by_count":36,"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":"2401.12873","title":"Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model","created":"2024-01-23","cited_by_count":33,"area":"alignment"},{"id":"2402.15754","title":"HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition","created":"2024-02-24","cited_by_count":33,"area":"alignment"},{"id":"2309.11166","title":"Are Large Language Models Really Robust to Word-Level Perturbations?","created":"2023-09-20","cited_by_count":32,"area":"alignment"},{"id":"2402.04229","title":"MusicRL: Aligning Music Generation to Human Preferences","created":"2024-02-06","cited_by_count":32,"area":"alignment"},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","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":"2305.01918","title":"Improving Contrastive Learning of Sentence Embeddings from AI Feedback","created":"2023-05-03","cited_by_count":29,"area":"alignment"},{"id":"2311.06503","title":"Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering","created":"2023-11-11","cited_by_count":29,"area":"alignment"},{"id":"2406.05587","title":"Creativity Has Left the Chat: The Price of Debiasing Language Models","created":"2024-06-08","cited_by_count":29,"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":"2401.16332","title":"Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods","created":"2024-01-29","cited_by_count":28,"area":"alignment"},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26,"area":"alignment"},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2504.07532","title":"AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation","created":"2025-04-10","cited_by_count":25,"area":"alignment"},{"id":"2402.18120","title":"Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?","created":"2024-02-28","cited_by_count":24,"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":"2506.02095","title":"Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences","created":"2025-06-02","cited_by_count":22,"area":"alignment"},{"id":"2506.09996","title":"From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring","created":"2025-06-11","cited_by_count":22,"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":"2310.01045","title":"Tool-Augmented Reward Modeling","created":"2023-10-02","cited_by_count":20,"area":"alignment"},{"id":"2508.07768","title":"Pareto Multi-Objective Alignment for Language Models","created":"2025-08-11","cited_by_count":20,"area":"alignment"},{"id":"1912.03553","title":"Learning Norms from Stories: A Prior for Value Aligned Agents","created":"2019-12-07","cited_by_count":19,"area":"alignment"},{"id":"2202.09662","title":"Reward Modeling for Mitigating Toxicity in Transformer-based Language Models","created":"2022-02-19","cited_by_count":18,"area":"alignment"},{"id":"2504.06141","title":"Adversarial Training of Reward Models","created":"2025-04-08","cited_by_count":18,"area":"alignment"},{"id":"2410.18027","title":"Cross-lingual Transfer of Reward Models in Multilingual Alignment","created":"2024-10-23","cited_by_count":17,"area":"alignment"},{"id":"2302.05721","title":"Synthesizing Human Gaze Feedback for Improved NLP Performance","created":"2023-02-11","cited_by_count":16,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2310.03013","title":"SemiReward: A General Reward Model for Semi-supervised Learning","created":"2023-10-04","cited_by_count":14,"area":"alignment"},{"id":"2311.10947","title":"RecExplainer: Aligning Large Language Models for Explaining Recommendation Models","created":"2023-11-18","cited_by_count":14,"area":"alignment"},{"id":"2204.05512","title":"Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference Feedback","created":"2022-04-12","cited_by_count":13,"area":"alignment"},{"id":"2409.04340","title":"AGR: Age Group fairness Reward for Bias Mitigation in LLMs","created":"2024-09-06","cited_by_count":12,"area":"alignment"},{"id":"2409.17472","title":"Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards","created":"2024-09-26","cited_by_count":12,"area":"alignment"},{"id":"2406.17923","title":"PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuning","created":"2024-06-25","cited_by_count":11,"area":"alignment"},{"id":"2406.18346","title":"AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations","created":"2024-06-26","cited_by_count":11,"area":"alignment"},{"id":"2412.15289","title":"SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage","created":"2024-12-19","cited_by_count":11,"area":"alignment"},{"id":"2407.19829","title":"Generative Retrieval with Preference Optimization for E-commerce Search","created":"2024-07-29","cited_by_count":10,"area":"alignment"},{"id":"2307.10512","title":"IvyGPT: InteractiVe Chinese pathwaY language model in medical domain","created":"2023-07-20","cited_by_count":9,"area":"alignment"},{"id":"2410.05656","title":"On the Modeling Capabilities of Large Language Models for Sequential Decision Making","created":"2024-10-08","cited_by_count":9,"area":"alignment"},{"id":"2508.05775","title":"Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM","created":"2025-08-07","cited_by_count":9,"area":"alignment"},{"id":"2308.11171","title":"ViCo: Engaging Video Comment Generation with Human Preference Rewards","created":"2023-08-22","cited_by_count":8,"area":"alignment"},{"id":"2307.10867","title":"FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback","created":"2023-07-20","cited_by_count":7,"area":"alignment"},{"id":"2310.00898","title":"Enabling Language Models to Implicitly Learn Self-Improvement","created":"2023-10-02","cited_by_count":7,"area":"alignment"},{"id":"2412.03253","title":"Alignment at Pre-training! Towards Native Alignment for Arabic LLMs","created":"2024-12-04","cited_by_count":7,"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":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2508.08509","title":"Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression","created":"2025-08-11","cited_by_count":7,"area":"alignment"},{"id":"2404.11095","title":"Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues","created":"2024-04-17","cited_by_count":6,"area":"alignment"},{"id":"2406.05902","title":"Whose Preferences? Differences in Fairness Preferences and Their Impact on the Fairness of AI Utilizing Human Feedback","created":"2024-06-09","cited_by_count":6,"area":"alignment"},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2410.15096","title":"GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2506.16502","title":"Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples","created":"2025-06-19","cited_by_count":6,"area":"alignment"},{"id":"2510.23751","title":"Debiasing Reward Models by Representation Learning with Guarantees","created":"2025-10-27","cited_by_count":6,"area":"alignment"},{"id":"2310.15477","title":"CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model","created":"2023-10-24","cited_by_count":5,"area":"alignment"},{"id":"2405.20053","title":"Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads","created":"2024-05-30","cited_by_count":5,"area":"alignment"},{"id":"2407.04185","title":"HAF-RM: A Hybrid Alignment Framework for Reward Model Training","created":"2024-07-04","cited_by_count":5,"area":"alignment"},{"id":"2410.04503","title":"LRHP: Learning Representations for Human Preferences via Preference Pairs","created":"2024-10-06","cited_by_count":5,"area":"alignment"},{"id":"2508.02618","title":"Alleviating Attention Hacking in Discriminative Reward Modeling through Interaction Distillation","created":"2025-08-04","cited_by_count":5,"area":"alignment"},{"id":"2510.17833","title":"Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage","created":"2025-10-03","cited_by_count":5,"area":"alignment"},{"id":"2404.00978","title":"Prior Constraints-based Reward Model Training for Aligning Large Language Models","created":"2024-04-01","cited_by_count":4,"area":"alignment"},{"id":"2406.11581","title":"Style Transfer with Multi-iteration Preference Optimization","created":"2024-06-17","cited_by_count":4,"area":"alignment"},{"id":"2409.17169","title":"REAL: Response Embedding-based Alignment for LLMs","created":"2024-09-17","cited_by_count":4,"area":"alignment"},{"id":"2503.19201","title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF","created":"2025-03-24","cited_by_count":4,"area":"alignment"},{"id":"2504.09895","title":"Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data","created":"2025-04-14","cited_by_count":4,"area":"alignment"},{"id":"2510.08048","title":"TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance","created":"2025-10-09","cited_by_count":4,"area":"alignment"},{"id":"2511.15767","title":"TB or Not TB: Coverage-Driven Direct Preference Optimization for Verilog Stimulus Generation","created":"2025-11-19","cited_by_count":4,"area":"alignment"},{"id":"2310.13385","title":"Tuna: Instruction Tuning using Feedback from Large Language Models","created":"2023-10-20","cited_by_count":3,"area":"alignment"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2406.14457","title":"Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue","created":"2024-06-20","cited_by_count":3,"area":"alignment"},{"id":"2503.10927","title":"OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses","created":"2025-03-13","cited_by_count":3,"area":"alignment"},{"id":"2504.10002","title":"FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions","created":"2025-04-14","cited_by_count":3,"area":"alignment"},{"id":"2507.16951","title":"Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs","created":"2025-07-22","cited_by_count":3,"area":"alignment"},{"id":"2507.18802","title":"DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition","created":"2025-07-24","cited_by_count":3,"area":"alignment"}],"next_cursor":"100"}