{"total":187,"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":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184,"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":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"area":"alignment"},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681,"area":"alignment"},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562,"area":"alignment"},{"id":"2310.16944","title":"Zephyr: Direct Distillation of LM Alignment","created":"2023-10-25","cited_by_count":506,"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":"2310.01377","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","created":"2023-10-02","cited_by_count":406,"area":"alignment"},{"id":"2312.15685","title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning","created":"2023-12-25","cited_by_count":364,"area":"alignment"},{"id":"2402.13228","title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","created":"2024-02-20","cited_by_count":241,"area":"alignment"},{"id":"2405.00675","title":"Self-Play Preference Optimization for Language Model Alignment","created":"2024-05-01","cited_by_count":232,"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":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195,"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":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178,"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":"2411.01111","title":"Rule Based Rewards for Language Model Safety","created":"2024-11-02","cited_by_count":108,"area":"alignment"},{"id":"2401.18058","title":"LongAlign: A Recipe for Long Context Alignment of Large Language Models","created":"2024-01-31","cited_by_count":106,"area":"alignment"},{"id":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106,"area":"alignment"},{"id":"2402.04833","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","created":"2024-02-07","cited_by_count":85,"area":"alignment"},{"id":"2402.05369","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","created":"2024-02-08","cited_by_count":85,"area":"alignment"},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69,"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":"2405.19332","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","created":"2024-05-29","cited_by_count":63,"area":"alignment"},{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63,"area":"alignment"},{"id":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57,"area":"alignment"},{"id":"2405.09719","title":"Spectral Editing of Activations for Large Language Model Alignment","created":"2024-05-15","cited_by_count":56,"area":"alignment"},{"id":"2406.01462","title":"The Importance of Online Data: Understanding Preference Fine-tuning via Coverage","created":"2024-06-03","cited_by_count":55,"area":"alignment"},{"id":"2402.10038","title":"RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models","created":"2024-02-15","cited_by_count":48,"area":"alignment"},{"id":"2403.19270","title":"sDPO: Don't Use Your Data All at Once","created":"2024-03-28","cited_by_count":46,"area":"alignment"},{"id":"2408.06266","title":"Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment","created":"2024-08-12","cited_by_count":46,"area":"alignment"},{"id":"2407.00617","title":"Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning","created":"2024-06-30","cited_by_count":45,"area":"alignment"},{"id":"2402.09401","title":"Reinforcement Learning from Human Feedback with Active Queries","created":"2024-02-14","cited_by_count":43,"area":"alignment"},{"id":"2407.02552","title":"RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs","created":"2024-07-02","cited_by_count":43,"area":"alignment"},{"id":"2503.03710","title":"Improving LLM Safety Alignment with Dual-Objective Optimization","created":"2025-03-05","cited_by_count":43,"area":"alignment"},{"id":"2410.06961","title":"Self-Boosting Large Language Models with Synthetic Preference Data","created":"2024-10-09","cited_by_count":40,"area":"alignment"},{"id":"2404.16792","title":"Model Extrapolation Expedites Alignment","created":"2024-04-25","cited_by_count":37,"area":"alignment"},{"id":"2404.14723","title":"Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks","created":"2024-04-23","cited_by_count":35,"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":"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":"2309.11166","title":"Are Large Language Models Really Robust to Word-Level Perturbations?","created":"2023-09-20","cited_by_count":32,"area":"alignment"},{"id":"2405.17888","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment","created":"2024-05-28","cited_by_count":32,"area":"alignment"},{"id":"2406.11801","title":"Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations","created":"2024-06-17","cited_by_count":32,"area":"alignment"},{"id":"2406.16235","title":"Preference Tuning For Toxicity Mitigation Generalizes Across Languages","created":"2024-06-23","cited_by_count":31,"area":"alignment"},{"id":"2409.17407","title":"Post-hoc Reward Calibration: A Case Study on Length Bias","created":"2024-09-25","cited_by_count":29,"area":"alignment"},{"id":"2603.12273","title":"Aligning Language Models from User Interactions","created":"2026-02-18","cited_by_count":28,"area":"alignment"},{"id":"2311.08685","title":"Safer-Instruct: Aligning Language Models with Automated Preference Data","created":"2023-11-15","cited_by_count":27,"area":"alignment"},{"id":"2408.04655","title":"Strong and weak alignment of large language models with human values","created":"2024-08-05","cited_by_count":27,"area":"alignment"},{"id":"2501.12735","title":"Online Preference Alignment for Language Models via Count-based Exploration","created":"2025-01-22","cited_by_count":26,"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":"2502.16852","title":"Improving LLM General Preference Alignment via Optimistic Online Mirror Descent","created":"2025-02-24","cited_by_count":24,"area":"alignment"},{"id":"2511.01689","title":"Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI","created":"2025-11-03","cited_by_count":24,"area":"alignment"},{"id":"2502.11555","title":"Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models","created":"2025-02-17","cited_by_count":22,"area":"alignment"},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"id":"2412.03881","title":"Weak-to-Strong Generalization Through the Data-Centric Lens","created":"2024-12-05","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":"2401.03129","title":"Examining Forgetting in Continual Pre-training of Aligned Large Language Models","created":"2024-01-06","cited_by_count":18,"area":"alignment"},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18,"area":"alignment"},{"id":"2405.07101","title":"Advanced Natural-based interaction for the ITAlian language: LLaMAntino-3-ANITA","created":"2024-05-11","cited_by_count":17,"area":"alignment"},{"id":"2405.13820","title":"Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching","created":"2024-05-22","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":"2406.10288","title":"Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models","created":"2024-06-12","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":"2408.04614","title":"Better Alignment with Instruction Back-and-Forth Translation","created":"2024-08-08","cited_by_count":16,"area":"alignment"},{"id":"2402.07896","title":"Suppressing Pink Elephants with Direct Principle Feedback","created":"2024-02-12","cited_by_count":15,"area":"alignment"},{"id":"2403.02513","title":"Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF","created":"2024-03-04","cited_by_count":15,"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":"2507.21183","title":"MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge","created":"2025-07-27","cited_by_count":15,"area":"alignment"},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2501.03884","title":"AlphaPO: Reward Shape Matters for LLM Alignment","created":"2025-01-07","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":"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":"2407.16637","title":"Course-Correction: Safety Alignment Using Synthetic Preferences","created":"2024-07-23","cited_by_count":13,"area":"alignment"},{"id":"2410.15483","title":"Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization Perspective","created":"2024-10-20","cited_by_count":12,"area":"alignment"},{"id":"2406.07657","title":"OPTune: Efficient Online Preference Tuning","created":"2024-06-11","cited_by_count":10,"area":"alignment"},{"id":"2510.01243","title":"Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing","created":"2025-09-24","cited_by_count":10,"area":"alignment"},{"id":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2407.03051","title":"Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment","created":"2024-07-03","cited_by_count":9,"area":"alignment"},{"id":"2410.05102","title":"SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks","created":"2024-10-07","cited_by_count":9,"area":"alignment"},{"id":"2410.11055","title":"Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only","created":"2024-10-14","cited_by_count":9,"area":"alignment"},{"id":"2410.20727","title":"Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment","created":"2024-10-28","cited_by_count":9,"area":"alignment"},{"id":"2502.16825","title":"Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization","created":"2025-02-24","cited_by_count":9,"area":"alignment"},{"id":"2503.04647","title":"Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment","created":"2025-03-06","cited_by_count":9,"area":"alignment"},{"id":"2505.12225","title":"Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling","created":"2025-05-18","cited_by_count":9,"area":"alignment"},{"id":"2505.17072","title":"Safety Alignment Can Be Not Superficial With Explicit Safety Signals","created":"2025-05-19","cited_by_count":9,"area":"alignment"},{"id":"2512.13655","title":"Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation","created":"2025-12-15","cited_by_count":9,"area":"alignment"},{"id":"2502.00666","title":"Avoiding $\\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration","created":"2025-02-02","cited_by_count":8,"area":"alignment"},{"id":"2505.13878","title":"InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models","created":"2025-05-20","cited_by_count":8,"area":"alignment"},{"id":"2603.06604","title":"Know When You're Wrong: Aligning Confidence with Correctness for LLM Error Detection","created":"2026-02-18","cited_by_count":8,"area":"alignment"},{"id":"2404.04291","title":"Investigating Regularization of Self-Play Language Models","created":"2024-04-04","cited_by_count":7,"area":"alignment"},{"id":"2405.20830","title":"Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2405.21040","title":"Direct Alignment of Language Models via Quality-Aware Self-Refinement","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2505.18720","title":"Optimal Transport-Based Token Weighting scheme for Enhanced Preference Optimization","created":"2025-05-24","cited_by_count":7,"area":"alignment"},{"id":"2509.23102","title":"Multiplayer Nash Preference Optimization","created":"2025-09-27","cited_by_count":7,"area":"alignment"},{"id":"2512.23461","title":"Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance","created":"2025-12-29","cited_by_count":7,"area":"alignment"}],"next_cursor":"100"}