{"total":394,"rows":[{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053,"area":"lr"},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"area":"alignment"},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562,"area":"alignment"},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264,"area":"lr"},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246,"area":"lr"},{"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":"2402.17733","title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks","created":"2024-02-27","cited_by_count":206,"area":null},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2406.00832","title":"BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling","created":"2024-06-02","cited_by_count":121,"area":"alignment"},{"id":"2412.14167","title":"VideoDPO: Omni-Preference Alignment for Video Diffusion Generation","created":"2024-12-18","cited_by_count":108,"area":"diffusion"},{"id":"2406.09279","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","created":"2024-06-13","cited_by_count":107,"area":"lr"},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"area":null},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"id":"2401.13136","title":"The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts","created":"2024-01-23","cited_by_count":94,"area":"alignment"},{"id":"2406.11839","title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models","created":"2024-06-17","cited_by_count":92,"area":"mllm"},{"id":"2503.16252","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","created":"2025-03-20","cited_by_count":83,"area":"lr"},{"id":"2406.03949","title":"UltraMedical: Building Specialized Generalists in Biomedicine","created":"2024-06-06","cited_by_count":67,"area":null},{"id":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67,"area":"alignment"},{"id":"2501.09695","title":"Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key","created":"2025-01-16","cited_by_count":65,"area":"mllm"},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64,"area":"alignment"},{"id":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63,"area":"moe"},{"id":"2506.03136","title":"Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning","created":"2025-06-03","cited_by_count":56,"area":null},{"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":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"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":"2410.15522","title":"M-RewardBench: Evaluating Reward Models in Multilingual Settings","created":"2024-10-20","cited_by_count":50,"area":"alignment"},{"id":"2405.11804","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","created":"2024-05-20","cited_by_count":49,"area":"agents"},{"id":"2405.19534","title":"Preference Learning Algorithms Do Not Learn Preference Rankings","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2406.06424","title":"Margin-aware Preference Optimization for Aligning Diffusion Models without Reference","created":"2024-06-10","cited_by_count":46,"area":"diffusion"},{"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":"2505.12929","title":"Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs","created":"2025-05-19","cited_by_count":44,"area":"lr"},{"id":"2410.05318","title":"Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification","created":"2024-10-05","cited_by_count":40,"area":"lr"},{"id":"2506.17080","title":"Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs","created":"2025-06-20","cited_by_count":40,"area":null},{"id":"2509.17940","title":"DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving","created":"2025-09-22","cited_by_count":39,"area":"driving"},{"id":"2502.02481","title":"Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study","created":"2025-02-04","cited_by_count":38,"area":null},{"id":"2404.16792","title":"Model Extrapolation Expedites Alignment","created":"2024-04-25","cited_by_count":37,"area":"alignment"},{"id":"2502.09650","title":"Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples","created":"2025-02-11","cited_by_count":37,"area":"alignment"},{"id":"2504.14218","title":"Understanding the Repeat Curse in Large Language Models from a Feature Perspective","created":"2025-04-19","cited_by_count":37,"area":"mechinterp"},{"id":"2410.03115","title":"X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale","created":"2024-10-04","cited_by_count":36,"area":null},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"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":"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":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","cited_by_count":33,"area":"safety"},{"id":"2406.10957","title":"Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence","created":"2024-06-16","cited_by_count":31,"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":"2410.10148","title":"AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization","created":"2024-10-14","cited_by_count":29,"area":"alignment"},{"id":"2501.06521","title":"Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering","created":"2025-01-11","cited_by_count":28,"area":null},{"id":"2404.15846","title":"From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models","created":"2024-04-24","cited_by_count":27,"area":null},{"id":"2409.19605","title":"The Crucial Role of Samplers in Online Direct Preference Optimization","created":"2024-09-29","cited_by_count":27,"area":"alignment"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2402.01469","title":"AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback","created":"2024-02-02","cited_by_count":25,"area":"agents"},{"id":"2404.01054","title":"Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment","created":"2024-04-01","cited_by_count":25,"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":"2506.14175","title":"GRAM: A Generative Foundation Reward Model for Reward Generalization","created":"2025-06-17","cited_by_count":25,"area":"alignment"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"area":"lr"},{"id":"2407.13709","title":"Understanding Reference Policies in Direct Preference Optimization","created":"2024-07-18","cited_by_count":22,"area":"alignment"},{"id":"2410.07672","title":"MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization","created":"2024-10-10","cited_by_count":22,"area":"agents"},{"id":"2406.19774","title":"Direct Preference Knowledge Distillation for Large Language Models","created":"2024-06-28","cited_by_count":21,"area":"alignment"},{"id":"2507.13618","title":"Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters","created":"2025-07-18","cited_by_count":21,"area":null},{"id":"2410.04203","title":"RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization","created":"2024-10-05","cited_by_count":19,"area":"alignment"},{"id":"2410.21662","title":"$f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization","created":"2024-10-29","cited_by_count":19,"area":"alignment"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2405.14953","title":"MallowsPO: Fine-Tune Your LLM with Preference Dispersions","created":"2024-05-23","cited_by_count":18,"area":"alignment"},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2404.14122","title":"Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice?","created":"2024-04-22","cited_by_count":17,"area":null},{"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":"2506.17252","title":"Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization","created":"2025-06-08","cited_by_count":17,"area":"alignment"},{"id":"2507.00018","title":"Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections","created":"2025-06-15","cited_by_count":17,"area":"alignment"},{"id":"2405.18348","title":"Can Automatic Metrics Assess High-Quality Translations?","created":"2024-05-28","cited_by_count":16,"area":null},{"id":"2406.00049","title":"QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation","created":"2024-05-28","cited_by_count":16,"area":null},{"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":"2503.08942","title":"Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback","created":"2025-03-11","cited_by_count":16,"area":"alignment"},{"id":"2505.14140","title":"RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning","created":"2025-05-20","cited_by_count":16,"area":"lr"},{"id":"2505.14279","title":"YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering","created":"2025-05-20","cited_by_count":16,"area":null},{"id":"2506.07171","title":"RULE: Reinforcement UnLEarning Achieves Forget-Retain Pareto Optimality","created":"2025-06-08","cited_by_count":16,"area":"safety"},{"id":"2501.11463","title":"Curiosity-Driven Reinforcement Learning from Human Feedback","created":"2025-01-20","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":"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":"2501.03884","title":"AlphaPO: Reward Shape Matters for LLM Alignment","created":"2025-01-07","cited_by_count":14,"area":"alignment"},{"id":"2502.11026","title":"RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment","created":"2025-02-16","cited_by_count":14,"area":"alignment"},{"id":"2503.04554","title":"Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation","created":"2025-03-06","cited_by_count":14,"area":null},{"id":"2407.15343","title":"Improving Minimum Bayes Risk Decoding with Multi-Prompt","created":"2024-07-22","cited_by_count":13,"area":null},{"id":"2412.02685","title":"T-REG: Preference Optimization with Token-Level Reward Regularization","created":"2024-12-03","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":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13,"area":"alignment"},{"id":"2505.05465","title":"ComPO: Preference Alignment via Comparison Oracles","created":"2025-05-08","cited_by_count":13,"area":"alignment"},{"id":"2506.03690","title":"Robust Preference Optimization via Dynamic Target Margins","created":"2025-06-04","cited_by_count":13,"area":"alignment"},{"id":"2404.04809","title":"Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Language","created":"2024-04-07","cited_by_count":12,"area":"rag"},{"id":"2406.15741","title":"Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level","created":"2024-06-22","cited_by_count":12,"area":null},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"id":"2507.16248","title":"FinResearchBench: A Logic Tree based Agent-as-a-Judge Evaluation Framework for Financial Research Agents","created":"2025-07-22","cited_by_count":12,"area":"agents"},{"id":"2508.18312","title":"What Matters in Data for DPO?","created":"2025-08-23","cited_by_count":12,"area":"alignment"},{"id":"2510.13809","title":"PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning","created":"2025-10-15","cited_by_count":12,"area":"wm"},{"id":"2403.08043","title":"Authorship Style Transfer with Policy Optimization","created":"2024-03-12","cited_by_count":11,"area":null},{"id":"2411.05986","title":"Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappings","created":"2024-11-08","cited_by_count":11,"area":"alignment"},{"id":"2411.12843","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","created":"2024-11-19","cited_by_count":11,"area":"alignment"},{"id":"2503.04369","title":"Lost in Literalism: How Supervised Training Shapes Translationese in LLMs","created":"2025-03-06","cited_by_count":11,"area":null}],"next_cursor":"100"}