{"total":216,"rows":[{"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":"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":"2310.16944","title":"Zephyr: Direct Distillation of LM Alignment","created":"2023-10-25","cited_by_count":506,"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":"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":"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":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115,"area":"alignment"},{"id":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109,"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":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"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":"2405.19320","title":"Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF","created":"2024-05-29","cited_by_count":73,"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":"2501.19309","title":"Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment","created":"2025-01-31","cited_by_count":59,"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":"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":"2412.14516","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","created":"2024-12-19","cited_by_count":51,"area":"alignment"},{"id":"2404.02655","title":"Calibrating the Confidence of Large Language Models by Eliciting Fidelity","created":"2024-04-03","cited_by_count":47,"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":"2402.09401","title":"Reinforcement Learning from Human Feedback with Active Queries","created":"2024-02-14","cited_by_count":43,"area":"alignment"},{"id":"2406.14563","title":"Model Merging and Safety Alignment: One Bad Model Spoils the Bunch","created":"2024-06-20","cited_by_count":43,"area":"alignment"},{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","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":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"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":"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":"2409.15360","title":"Reward-Robust RLHF in LLMs","created":"2024-09-18","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":"2505.23556","title":"Understanding Refusal in Language Models with Sparse Autoencoders","created":"2025-05-29","cited_by_count":29,"area":"alignment"},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28,"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":"2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","created":"2025-02-02","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":"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":"2602.01539","title":"MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety","created":"2026-02-02","cited_by_count":21,"area":"alignment"},{"id":"2402.05000","title":"Pedagogical Alignment of Large Language Models","created":"2024-02-07","cited_by_count":19,"area":"alignment"},{"id":"2509.01909","title":"Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models","created":"2025-09-02","cited_by_count":19,"area":"alignment"},{"id":"2602.17560","title":"ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment","created":"2026-02-19","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":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","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":"2505.22338","title":"Text2Grad: Reinforcement Learning from Natural Language Feedback","created":"2025-05-28","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":"2502.16182","title":"IPO: Your Language Model is Secretly a Preference Classifier","created":"2025-02-22","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":"2410.10093","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","created":"2024-10-14","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":"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":"2510.01555","title":"Rethinking KL Regularization in RLHF: From Value Estimation to Gradient Optimization","created":"2025-10-02","cited_by_count":14,"area":"alignment"},{"id":"2412.09544","title":"Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking","created":"2024-12-12","cited_by_count":13,"area":"alignment"},{"id":"2503.05079","title":"On a Connection Between Imitation Learning and RLHF","created":"2025-03-07","cited_by_count":13,"area":"alignment"},{"id":"2505.17196","title":"Shape it Up! Restoring LLM Safety during Finetuning","created":"2025-05-22","cited_by_count":11,"area":"alignment"},{"id":"2410.08067","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","created":"2024-10-10","cited_by_count":10,"area":"alignment"},{"id":"2506.06964","title":"Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization","created":"2025-06-08","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":"2410.05102","title":"SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks","created":"2024-10-07","cited_by_count":9,"area":"alignment"},{"id":"2410.18533","title":"LOGO -- Long cOntext aliGnment via efficient preference Optimization","created":"2024-10-24","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":"2504.15477","title":"In-context Ranking Preference Optimization","created":"2025-04-21","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":"2311.07723","title":"Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains","created":"2023-11-13","cited_by_count":8,"area":"alignment"},{"id":"2405.11870","title":"Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process","created":"2024-05-20","cited_by_count":8,"area":"alignment"},{"id":"2409.06411","title":"Length Desensitization in Direct Preference Optimization","created":"2024-09-10","cited_by_count":8,"area":"alignment"},{"id":"2410.14676","title":"SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment","created":"2024-10-18","cited_by_count":8,"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":"2502.05478","title":"OntoTune: Ontology-Driven Self-training for Aligning Large Language Models","created":"2025-02-08","cited_by_count":8,"area":"alignment"},{"id":"2505.12762","title":"IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment","created":"2025-05-19","cited_by_count":8,"area":"alignment"},{"id":"2509.23873","title":"Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":8,"area":"alignment"},{"id":"2512.20806","title":"Safety Alignment of LMs via Non-cooperative Games","created":"2025-12-23","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":"2505.04993","title":"Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes","created":"2025-05-08","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"}],"next_cursor":"100"}