{"total":69,"rows":[{"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":"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":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67,"area":"alignment"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"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":"2408.06266","title":"Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment","created":"2024-08-12","cited_by_count":46,"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":"2410.04350","title":"TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights","created":"2024-10-06","cited_by_count":42,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2506.03517","title":"DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models","created":"2025-06-04","cited_by_count":34,"area":"diffusion"},{"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":"2410.15334","title":"Modality-Fair Preference Optimization for Trustworthy MLLM Alignment","created":"2024-10-20","cited_by_count":26,"area":"mllm"},{"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":"2410.16531","title":"Bayesian scaling laws for in-context learning","created":"2024-10-21","cited_by_count":19,"area":"safety"},{"id":"2412.09243","title":"SPRec: Self-Play to Debias LLM-based Recommendation","created":"2024-12-12","cited_by_count":18,"area":"synth"},{"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":"2409.09774","title":"Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization","created":"2024-09-15","cited_by_count":15,"area":"alignment"},{"id":"2507.00841","title":"SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents","created":"2025-07-01","cited_by_count":15,"area":"safety"},{"id":"2502.02088","title":"Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video Generation","created":"2025-02-04","cited_by_count":13,"area":"diffusion"},{"id":"2505.19770","title":"Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO","created":"2025-05-26","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":"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":"2409.06411","title":"Length Desensitization in Direct Preference Optimization","created":"2024-09-10","cited_by_count":8,"area":"alignment"},{"id":"2502.09183","title":"RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation","created":"2025-02-13","cited_by_count":8,"area":"lr"},{"id":"2406.12606","title":"Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment","created":"2024-06-18","cited_by_count":7,"area":"alignment"},{"id":"2506.00042","title":"Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists","created":"2025-05-28","cited_by_count":7,"area":"agents"},{"id":"2512.07175","title":"SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models","created":"2025-12-08","cited_by_count":7,"area":"synth"},{"id":"2409.12741","title":"Fine Tuning Large Language Models for Medicine: The Role and Importance of Direct Preference Optimization","created":"2024-09-19","cited_by_count":6,"area":"alignment"},{"id":"2410.15096","title":"GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2411.05199","title":"CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement","created":"2024-11-07","cited_by_count":6,"area":null},{"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":"2411.03700","title":"The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models","created":"2024-11-06","cited_by_count":5,"area":"alignment"},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"},{"id":"2411.05875","title":"Towards Improved Preference Optimization Pipeline: from Data Generation to Budget-Controlled Regularization","created":"2024-11-07","cited_by_count":4,"area":"alignment"},{"id":"2411.08923","title":"Aligning Visual Contrastive learning models via Preference Optimization","created":"2024-11-12","cited_by_count":4,"area":"alignment"},{"id":"2411.14797","title":"Continual SFT Matches Multimodal RLHF with Negative Supervision","created":"2024-11-22","cited_by_count":4,"area":"mllm"},{"id":"2502.13603","title":"Efficient Safety Retrofitting Against Jailbreaking for LLMs","created":"2025-02-19","cited_by_count":4,"area":"alignment"},{"id":"2508.15868","title":"CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning","created":"2025-08-21","cited_by_count":4,"area":"lr"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2409.10571","title":"ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood","created":"2024-09-14","cited_by_count":3,"area":"alignment"},{"id":"2505.12435","title":"SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment","created":"2025-05-18","cited_by_count":3,"area":"alignment"},{"id":"2505.14299","title":"Empowering LLMs in Task-Oriented Dialogues: A Domain-Independent Multi-Agent Framework and Fine-Tuning Strategy","created":"2025-05-20","cited_by_count":3,"area":"agents"},{"id":"2506.00835","title":"SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning","created":"2025-06-01","cited_by_count":3,"area":"alignment"},{"id":"2506.13559","title":"Understand the Implication: Learning to Think for Pragmatic Understanding","created":"2025-06-16","cited_by_count":3,"area":"lr"},{"id":"2509.25762","title":"OPPO: Accelerating PPO-based RLHF via Pipeline Overlap","created":"2025-09-30","cited_by_count":3,"area":"alignment"},{"id":"2510.13022","title":"On the Role of Preference Variance in Preference Optimization","created":"2025-10-14","cited_by_count":3,"area":"alignment"},{"id":"2511.19049","title":"Beyond Reward Margin: Rethinking and Resolving Likelihood Displacement in Diffusion Models via Video Generation","created":"2025-11-24","cited_by_count":3,"area":"diffusion"},{"id":"2412.08393","title":"Learning to Reason via Self-Iterative Process Feedback for Small Language Models","created":"2024-12-11","cited_by_count":2,"area":"lr"},{"id":"2502.17507","title":"C2-DPO: Constrained Controlled Direct Preference Optimization","created":"2025-02-22","cited_by_count":2,"area":"alignment"},{"id":"2507.07723","title":"Stable Preference Optimization: A Bilevel Approach to Catastrophic Preference Shift","created":"2025-07-10","cited_by_count":2,"area":"alignment"},{"id":"2608.31079","title":"Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization","created":"2026-08-31","cited_by_count":2,"area":"alignment"},{"id":"2502.12066","title":"CONSTRUCTA: Automating Commercial Construction Schedules in Fabrication Facilities with Large Language Models","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2504.09058","title":"Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement","created":"2025-04-12","cited_by_count":1,"area":"lr"},{"id":"2505.23761","title":"Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2506.23273","title":"FinStat2SQL: A Text2SQL Pipeline for Financial Statement Analysis","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2508.14947","title":"Linear Preference Optimization: Decoupled Gradient Control via Absolute Regularization","created":"2025-08-20","cited_by_count":1,"area":"alignment"},{"id":"2601.20312","title":"SAPO: Self-Adaptive Process Optimization Makes Small Reasoners Stronger","created":"2026-01-28","cited_by_count":1,"area":"lr"},{"id":"2605.02626","title":"Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models","created":"2026-05-04","cited_by_count":1,"area":"alignment"},{"id":"2605.28440","title":"AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates","created":"2026-05-27","cited_by_count":1,"area":"alignment"},{"id":"2412.09280","title":"Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2505.21893","title":"SIPO: Stabilized and Improved Preference Optimization for Aligning Diffusion Models","created":"2025-05-28","cited_by_count":0,"area":"diffusion"},{"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":"2601.09718","title":"StatLLaMA: Multi-Stage training for domain-optimized statistical large language models","created":"2025-12-26","cited_by_count":0,"area":"alignment"},{"id":"2604.01787","title":"DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment","created":"2026-04-02","cited_by_count":0,"area":"alignment"},{"id":"2604.20933","title":"IRIS: Interpolative R\\'enyi Iterative Self-play for Large Language Model Fine-Tuning","created":"2026-04-22","cited_by_count":0,"area":"synth"},{"id":"2605.13229","title":"Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization","created":"2026-05-13","cited_by_count":0,"area":"alignment"},{"id":"2605.15012","title":"Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.26315","title":"Curriculum Learning for Safety Alignment","created":"2026-05-25","cited_by_count":0,"area":"alignment"}],"next_cursor":null}