{"total":122,"rows":[{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"area":"alignment"},{"id":"2501.09686","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","created":"2025-01-16","cited_by_count":293,"area":"wm"},{"id":"2411.19943","title":"Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability","created":"2024-11-29","cited_by_count":83,"area":"lr"},{"id":"2502.10391","title":"MM-RLHF: The Next Step Forward in Multimodal LLM Alignment","created":"2025-02-14","cited_by_count":83,"area":"mllm"},{"id":"2404.04626","title":"Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective","created":"2024-04-06","cited_by_count":69,"area":"alignment"},{"id":"2405.19316","title":"Robust Preference Optimization through Reward Model Distillation","created":"2024-05-29","cited_by_count":67,"area":"alignment"},{"id":"2406.09215","title":"On Softmax Direct Preference Optimization for Recommendation","created":"2024-06-13","cited_by_count":64,"area":"alignment"},{"id":"2502.16923","title":"A Systematic Survey of Automatic Prompt Optimization Techniques","created":"2025-02-24","cited_by_count":63,"area":null},{"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":"2505.20065","title":"SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety","created":"2025-05-26","cited_by_count":37,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2405.17346","title":"Prompt Optimization with Human Feedback","created":"2024-05-27","cited_by_count":35,"area":"alignment"},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"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":"2405.17931","title":"Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment","created":"2024-05-28","cited_by_count":28,"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":"2404.13846","title":"Filtered Direct Preference Optimization","created":"2024-04-22","cited_by_count":24,"area":"alignment"},{"id":"2406.07327","title":"3D-Properties: Identifying Challenges in DPO and Charting a Path Forward","created":"2024-06-11","cited_by_count":24,"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":"2504.00640","title":"POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation","created":"2025-04-01","cited_by_count":22,"area":"lr"},{"id":"2504.18397","title":"Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization","created":"2025-04-25","cited_by_count":22,"area":"lr"},{"id":"2406.00654","title":"Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback","created":"2024-06-02","cited_by_count":20,"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":"2405.14953","title":"MallowsPO: Fine-Tune Your LLM with Preference Dispersions","created":"2024-05-23","cited_by_count":18,"area":"alignment"},{"id":"2508.04349","title":"GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy","created":"2025-08-06","cited_by_count":18,"area":"lr"},{"id":"2506.17252","title":"Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization","created":"2025-06-08","cited_by_count":17,"area":"alignment"},{"id":"2404.00530","title":"Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization","created":"2024-03-31","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":"2410.05328","title":"Reward Learning From Preference With Ties","created":"2024-10-05","cited_by_count":14,"area":"alignment"},{"id":"2407.18676","title":"Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift","created":"2024-07-26","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":"2407.02243","title":"Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization","created":"2024-07-02","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":"2405.11647","title":"Hummer: Towards Limited Competitive Preference Dataset","created":"2024-05-19","cited_by_count":10,"area":"alignment"},{"id":"2412.10742","title":"WEPO: Web Element Preference Optimization for LLM-based Web Navigation","created":"2024-12-14","cited_by_count":10,"area":"alignment"},{"id":"2502.17057","title":"ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance","created":"2025-02-24","cited_by_count":10,"area":null},{"id":"2405.00747","title":"Soft Preference Optimization: Aligning Language Models to Expert Distributions","created":"2024-04-30","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":"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":"2504.03612","title":"AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset","created":"2025-04-04","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":"2510.23853","title":"Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception","created":"2025-10-27","cited_by_count":9,"area":"agents"},{"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":"2409.17431","title":"On Extending Direct Preference Optimization to Accommodate Ties","created":"2024-09-25","cited_by_count":8,"area":"alignment"},{"id":"2502.14272","title":"Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models","created":"2025-02-20","cited_by_count":8,"area":"lr"},{"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":"2406.06496","title":"Direct Preference Optimization for Suppressing Hallucinated Prior Exams in Radiology Report Generation","created":"2024-06-10","cited_by_count":7,"area":"mllm"},{"id":"2411.13904","title":"Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning","created":"2024-11-21","cited_by_count":7,"area":"agents"},{"id":"2405.16681","title":"Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization","created":"2024-05-26","cited_by_count":6,"area":"alignment"},{"id":"2410.20187","title":"Uncertainty-Penalized Direct Preference Optimization","created":"2024-10-26","cited_by_count":6,"area":"alignment"},{"id":"2502.00657","title":"LLM Safety Alignment is Divergence Estimation in Disguise","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2502.03429","title":"On Fairness of Unified Multimodal Large Language Model for Image Generation","created":"2025-02-05","cited_by_count":6,"area":"mllm"},{"id":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2506.07492","title":"Explicit Preference Optimization: No Need for an Implicit Reward Model","created":"2025-06-09","cited_by_count":6,"area":"alignment"},{"id":"2407.09072","title":"New Desiderata for Direct Preference Optimization","created":"2024-07-12","cited_by_count":5,"area":"alignment"},{"id":"2407.14477","title":"Data-Centric Human Preference with Rationales for Direct Preference Alignment","created":"2024-07-19","cited_by_count":5,"area":"alignment"},{"id":"2410.08458","title":"Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both","created":"2024-10-11","cited_by_count":5,"area":"alignment"},{"id":"2411.02442","title":"TODO: Enhancing LLM Alignment with Ternary Preferences","created":"2024-11-02","cited_by_count":5,"area":"alignment"},{"id":"2412.17696","title":"Understanding the Logic of Direct Preference Alignment through Logic","created":"2024-12-23","cited_by_count":5,"area":"alignment"},{"id":"2501.15007","title":"Controllable Protein Sequence Generation with LLM Preference Optimization","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2504.05321","title":"VALUE: Value-Aware Large Language Model for Query Rewriting via Weighted Trie in Sponsored Search","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2509.25717","title":"Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization","created":"2025-09-30","cited_by_count":5,"area":"mllm"},{"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":"2405.17956","title":"Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier","created":"2024-05-28","cited_by_count":4,"area":"alignment"},{"id":"2502.06861","title":"Design Considerations in Offline Preference-based RL","created":"2025-02-08","cited_by_count":4,"area":"alignment"},{"id":"2510.06652","title":"Aligning Large Language Models via Fully Self-Synthetic Data","created":"2025-10-08","cited_by_count":4,"area":"alignment"},{"id":"2510.26096","title":"ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models","created":"2025-10-30","cited_by_count":4,"area":"safety"},{"id":"2511.19168","title":"RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning","created":"2025-11-24","cited_by_count":4,"area":"lr"},{"id":"2604.08553","title":"GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback","created":"2026-03-11","cited_by_count":4,"area":null},{"id":"2411.14871","title":"Preference Alignment for Diffusion Model via Explicit Denoised Distribution Estimation","created":"2024-11-22","cited_by_count":3,"area":"diffusion"},{"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":"2506.01523","title":"Beyond RLHF: A Unified Theoretical Framework of Alignment","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2506.14157","title":"DCRM: A Heuristic to Measure Response Pair Quality in Preference Optimization","created":"2025-06-17","cited_by_count":3,"area":"alignment"},{"id":"2507.18858","title":"Weak-to-Strong Generalization with Failure Trajectories: A Tree-based Approach to Elicit Optimal Policy in Strong Models","created":"2025-07-25","cited_by_count":3,"area":null},{"id":"2508.11281","title":"ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection","created":"2025-08-15","cited_by_count":3,"area":null},{"id":"2604.12710","title":"LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety","created":"2026-04-13","cited_by_count":3,"area":"alignment"},{"id":"2604.17501","title":"CoAct: Co-Active LLM Preference Learning with Human-AI Synergy","created":"2026-04-19","cited_by_count":3,"area":"alignment"},{"id":"2605.10937","title":"Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping","created":"2026-05-11","cited_by_count":3,"area":"lr"},{"id":"2502.17507","title":"C2-DPO: Constrained Controlled Direct Preference Optimization","created":"2025-02-22","cited_by_count":2,"area":"alignment"},{"id":"2509.04897","title":"PLaMo 2 Technical Report","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2510.23590","title":"Lightweight Robust Direct Preference Optimization","created":"2025-10-27","cited_by_count":2,"area":"alignment"},{"id":"2605.08037","title":"Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph","created":"2026-05-08","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":"2505.24251","title":"Proactive Guidance of Multi-Turn Conversation in Industrial Search","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2506.02261","title":"What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context","created":"2025-06-02","cited_by_count":1,"area":"alignment"},{"id":"2508.08486","title":"Beyond Ordinal Preferences: Why Alignment Needs Cardinal Human Feedback","created":"2025-08-11","cited_by_count":1,"area":"alignment"},{"id":"2508.14947","title":"Linear Preference Optimization: Decoupled Gradient Control via Absolute Regularization","created":"2025-08-20","cited_by_count":1,"area":"alignment"},{"id":"2508.20038","title":"Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks","created":"2025-08-27","cited_by_count":1,"area":"alignment"},{"id":"2509.03526","title":"Enhancing Speech Large Language Models through Reinforced Behavior Alignment","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2509.22851","title":"Adaptive Margin RLHF via Preference over Preferences","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2603.01124","title":"ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models","created":"2026-03-01","cited_by_count":1,"area":"lr"},{"id":"2603.07211","title":"CompassDPO: Dynamics-Controlled Direct Preference Optimization for Robust Safety Alignment","created":"2026-03-07","cited_by_count":1,"area":"alignment"},{"id":"2604.21209","title":"Align Generative Artificial Intelligence with Human Preferences: A Novel Large Language Model Fine-Tuning Method for Online Review Management","created":"2026-04-23","cited_by_count":1,"area":"alignment"},{"id":"2605.08472","title":"Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models","created":"2026-05-08","cited_by_count":1,"area":"synth"},{"id":"2605.10784","title":"MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization","created":"2026-05-11","cited_by_count":1,"area":"alignment"},{"id":"2605.11974","title":"Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2406.10203","title":"A Probability--Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors","created":"2024-06-14","cited_by_count":0,"area":"alignment"},{"id":"2409.16779","title":"LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ","created":"2024-09-25","cited_by_count":0,"area":"lr"},{"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"}],"next_cursor":"100"}