{"total":54,"rows":[{"id":"2502.00674","title":"Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?","created":"2025-02-02","cited_by_count":54,"area":"lr"},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49,"area":"alignment"},{"id":"2506.17080","title":"Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs","created":"2025-06-20","cited_by_count":40,"area":null},{"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":"2410.04203","title":"RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization","created":"2024-10-05","cited_by_count":19,"area":"alignment"},{"id":"2412.02685","title":"T-REG: Preference Optimization with Token-Level Reward Regularization","created":"2024-12-03","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":"2606.22995","title":"Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning","created":"2026-06-22","cited_by_count":13,"area":"agents"},{"id":"2504.04524","title":"Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning","created":"2025-04-06","cited_by_count":12,"area":"lr"},{"id":"2509.19333","title":"Pluralistic Off-policy Evaluation and Alignment","created":"2025-09-15","cited_by_count":11,"area":"alignment"},{"id":"2502.00203","title":"Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment","created":"2025-01-31","cited_by_count":10,"area":"lr"},{"id":"2412.13862","title":"Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model","created":"2024-12-18","cited_by_count":9,"area":"alignment"},{"id":"2506.04463","title":"Aligning Large Language Models with Implicit Preferences from User-Generated Content","created":"2025-06-04","cited_by_count":9,"area":"alignment"},{"id":"2506.10054","title":"Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs","created":"2025-06-11","cited_by_count":9,"area":"alignment"},{"id":"2605.07260","title":"When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language Models","created":"2026-05-08","cited_by_count":9,"area":"moe"},{"id":"2409.06411","title":"Length Desensitization in Direct Preference Optimization","created":"2024-09-10","cited_by_count":8,"area":"alignment"},{"id":"2504.00623","title":"Efficient Construction of Model Family through Progressive Training Using Model Expansion","created":"2025-04-01","cited_by_count":8,"area":null},{"id":"2509.23102","title":"Multiplayer Nash Preference Optimization","created":"2025-09-27","cited_by_count":7,"area":"alignment"},{"id":"2503.04222","title":"FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion","created":"2025-03-06","cited_by_count":6,"area":"alignment"},{"id":"2507.15507","title":"Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback","created":"2025-07-21","cited_by_count":6,"area":"alignment"},{"id":"2410.09362","title":"SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins","created":"2024-10-12","cited_by_count":5,"area":"alignment"},{"id":"2502.17927","title":"Advantage-Guided Distillation for Preference Alignment in Small Language Models","created":"2025-02-25","cited_by_count":5,"area":"alignment"},{"id":"2503.23913","title":"Entropy-Based Adaptive Weighting for Self-Training","created":"2025-03-31","cited_by_count":5,"area":"lr"},{"id":"2602.02033","title":"One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation","created":"2026-02-02","cited_by_count":5,"area":"alignment"},{"id":"2503.15880","title":"InCo-DPO: Balancing Distribution Shift and Data Quality for Enhanced Preference Optimization","created":"2025-03-20","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":"2601.17329","title":"Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment","created":"2026-01-24","cited_by_count":4,"area":"alignment"},{"id":"2501.06645","title":"FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings","created":"2025-01-11","cited_by_count":3,"area":"alignment"},{"id":"2511.06222","title":"SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization","created":"2025-11-09","cited_by_count":3,"area":"alignment"},{"id":"2601.00623","title":"DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations","created":"2026-01-02","cited_by_count":3,"area":"mllm"},{"id":"2409.18417","title":"VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedback","created":"2024-09-27","cited_by_count":2,"area":"alignment"},{"id":"2504.06659","title":"Leveraging Machine Unlearning for Cost-Efficient Preference Alignment","created":"2025-04-09","cited_by_count":2,"area":"alignment"},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2510.05342","title":"Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization","created":"2025-10-06","cited_by_count":1,"area":"alignment"},{"id":"2510.21090","title":"Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only","created":"2025-10-24","cited_by_count":1,"area":"alignment"},{"id":"2602.11902","title":"Mitigating Mismatch within Reference-based Preference Optimization","created":"2026-02-12","cited_by_count":1,"area":"alignment"},{"id":"2604.21380","title":"Conjecture and Inquiry: Quantifying Software Performance Requirements via Interactive Retrieval-Augmented Preference Elicitation","created":"2026-04-23","cited_by_count":1,"area":"rag"},{"id":"2605.15416","title":"Margin-Adaptive Confidence Ranking for Reliable LLM Judgement","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.26442","title":"Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2607.16240","title":"Normalized Rewards for Preference Optimization","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2409.17791","title":"Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness","created":"2024-09-26","cited_by_count":0,"area":"alignment"},{"id":"2507.20133","title":"Sem-DPO: Mitigating Semantic Inconsistency in Preference Optimization for Prompt Engineering","created":"2025-07-27","cited_by_count":0,"area":"alignment"},{"id":"2509.16965","title":"Preference Distillation via Value based Reinforcement Learning","created":"2025-09-21","cited_by_count":0,"area":"alignment"},{"id":"2509.24207","title":"Humanline: Online Alignment as Perceptual Loss","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2510.00647","title":"MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation","created":"2025-10-01","cited_by_count":0,"area":"alignment"},{"id":"2510.04096","title":"RLRF: Competitive Search Agent Design via Reinforcement Learning from Ranker Feedback","created":"2025-10-05","cited_by_count":0,"area":"agents"},{"id":"2601.06108","title":"From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models","created":"2026-01-03","cited_by_count":0,"area":"alignment"},{"id":"2603.04968","title":"When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger","created":"2026-03-05","cited_by_count":0,"area":"alignment"},{"id":"2603.04974","title":"VRM: Teaching Reward Models to Understand Authentic Human Preferences","created":"2026-03-05","cited_by_count":0,"area":"alignment"},{"id":"2605.31164","title":"D$^3$: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.09568","title":"Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.19598","title":"PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment","created":"2026-08-20","cited_by_count":0,"area":"alignment"},{"id":"2610.15097","title":"Anchors Enhance Controllability and Reasoning of Diffusion Language Models","created":"2026-10-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}