{"total":130,"rows":[{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942,"area":"moe"},{"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":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2412.15204","title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","created":"2024-12-19","cited_by_count":379,"area":"lr"},{"id":"2501.13918","title":"Improving Video Generation with Human Feedback","created":"2025-01-23","cited_by_count":284,"area":"diffusion"},{"id":"2507.01352","title":"Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy","created":"2025-07-02","cited_by_count":214,"area":"lr"},{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"id":"2507.18624","title":"Checklists Are Better Than Reward Models For Aligning Language Models","created":"2025-07-24","cited_by_count":128,"area":"alignment"},{"id":"2505.19591","title":"Multi-Agent Collaboration via Evolving Orchestration","created":"2025-05-26","cited_by_count":108,"area":"agents"},{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104,"area":"lr"},{"id":"2411.17451","title":"VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models","created":"2024-11-26","cited_by_count":86,"area":"alignment"},{"id":"2501.18099","title":"Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge","created":"2025-01-30","cited_by_count":78,"area":"lr"},{"id":"2412.15084","title":"AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling","created":"2024-12-19","cited_by_count":77,"area":"lr"},{"id":"2505.11475","title":"HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages","created":"2025-05-16","cited_by_count":75,"area":"alignment"},{"id":"2501.12368","title":"InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model","created":"2025-01-21","cited_by_count":74,"area":"lr"},{"id":"2411.16646","title":"Self-Generated Critiques Boost Reward Modeling for Language Models","created":"2024-11-25","cited_by_count":71,"area":"lr"},{"id":"2504.05228","title":"NoveltyBench: Evaluating Language Models for Humanlike Diversity","created":"2025-04-07","cited_by_count":66,"area":null},{"id":"2410.02683","title":"DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life","created":"2024-10-03","cited_by_count":59,"area":null},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54,"area":null},{"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":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37,"area":null},{"id":"2501.15602","title":"Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning","created":"2025-01-26","cited_by_count":36,"area":"lr"},{"id":"2503.13399","title":"MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research","created":"2025-03-17","cited_by_count":32,"area":"lr"},{"id":"2602.14069","title":"Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric","created":"2026-02-15","cited_by_count":27,"area":"alignment"},{"id":"2410.19133","title":"Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback","created":"2024-10-24","cited_by_count":26,"area":"alignment"},{"id":"2507.09075","title":"OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique","created":"2025-07-11","cited_by_count":25,"area":"lr"},{"id":"2412.03205","title":"U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs","created":"2024-12-04","cited_by_count":24,"area":null},{"id":"2412.13746","title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","created":"2024-12-18","cited_by_count":23,"area":"rag"},{"id":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","cited_by_count":23,"area":"alignment"},{"id":"2503.17439","title":"LEMMA: Learning from Errors for MatheMatical Advancement in LLMs","created":"2025-03-21","cited_by_count":21,"area":"lr"},{"id":"2505.14268","title":"Think-J: Learning to Think for Generative LLM-as-a-Judge","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2503.07478","title":"VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models","created":"2025-03-10","cited_by_count":19,"area":"lr"},{"id":"2504.06141","title":"Adversarial Training of Reward Models","created":"2025-04-08","cited_by_count":18,"area":"alignment"},{"id":"2411.19146","title":"Puzzle: Distillation-Based NAS for Inference-Optimized LLMs","created":"2024-11-28","cited_by_count":17,"area":null},{"id":"2503.04378","title":"HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks","created":"2025-03-06","cited_by_count":17,"area":"lr"},{"id":"2505.16265","title":"Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models","created":"2025-05-22","cited_by_count":16,"area":"lr"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2508.03550","title":"Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations","created":"2025-08-05","cited_by_count":15,"area":"alignment"},{"id":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2512.20578","title":"Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits","created":"2025-12-23","cited_by_count":14,"area":null},{"id":"2510.20369","title":"Ask a Strong LLM Judge when Your Reward Model is Uncertain","created":"2025-10-23","cited_by_count":13,"area":"alignment"},{"id":"2512.05111","title":"ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning","created":"2025-12-04","cited_by_count":13,"area":"lr"},{"id":"2410.16670","title":"CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing","created":"2024-10-22","cited_by_count":12,"area":"lr"},{"id":"2604.23626","title":"GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs","created":"2026-04-26","cited_by_count":12,"area":"agents"},{"id":"2504.12663","title":"Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment","created":"2025-04-17","cited_by_count":11,"area":"alignment"},{"id":"2602.04649","title":"Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models","created":"2026-02-04","cited_by_count":11,"area":"lr"},{"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":"2502.19731","title":"Preference Learning Unlocks LLMs' Psycho-Counseling Skills","created":"2025-02-27","cited_by_count":10,"area":"alignment"},{"id":"2506.19467","title":"Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?","created":"2025-06-24","cited_by_count":10,"area":"lr"},{"id":"2507.10540","title":"FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2507.21391","title":"Multimodal LLMs as Customized Reward Models for Text-to-Image Generation","created":"2025-07-28","cited_by_count":10,"area":"mllm"},{"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":"2505.23349","title":"Towards Reward Fairness in RLHF: From a Resource Allocation Perspective","created":"2025-05-29","cited_by_count":9,"area":"alignment"},{"id":"2506.10060","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2509.21319","title":"RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards","created":"2025-09-25","cited_by_count":8,"area":"alignment"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2501.08068","title":"A Roadmap to Guide the Integration of LLMs in Hierarchical Planning","created":"2025-01-14","cited_by_count":7,"area":"lr"},{"id":"2502.06329","title":"Expect the Unexpected: FailSafe Long Context QA for Finance","created":"2025-02-10","cited_by_count":7,"area":null},{"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":"2506.07434","title":"Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding","created":"2025-06-09","cited_by_count":7,"area":"alignment"},{"id":"2511.19097","title":"DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF","created":"2025-11-11","cited_by_count":7,"area":"lr"},{"id":"2506.02945","title":"Quantitative LLM Judges","created":"2025-06-03","cited_by_count":6,"area":null},{"id":"2507.00665","title":"SAFER: Probing Safety in Reward Models with Sparse Autoencoder","created":"2025-07-01","cited_by_count":6,"area":"alignment"},{"id":"2507.08068","title":"Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions","created":"2025-07-10","cited_by_count":6,"area":"lr"},{"id":"2507.19219","title":"How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework","created":"2025-07-25","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2510.06915","title":"LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling","created":"2025-10-08","cited_by_count":5,"area":"alignment"},{"id":"2602.19416","title":"IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking","created":"2026-02-23","cited_by_count":5,"area":"alignment"},{"id":"2503.11858","title":"OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2506.08235","title":"Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim $\\rightarrow$ Evidence Reasoning","created":"2025-06-09","cited_by_count":4,"area":"lr"},{"id":"2506.15498","title":"SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling","created":"2025-06-18","cited_by_count":4,"area":"lr"},{"id":"2508.00459","title":"Thinking Machines: Mathematical Reasoning in the Age of LLMs","created":"2025-08-01","cited_by_count":4,"area":"lr"},{"id":"2508.19922","title":"HEAL: A Hypothesis-Based Preference-Aware Analysis Framework","created":"2025-08-27","cited_by_count":4,"area":"alignment"},{"id":"2511.02463","title":"Extending RLVR to Open-Ended Tasks via Verifiable Multiple-Choice Reformulation","created":"2025-11-04","cited_by_count":4,"area":"lr"},{"id":"2512.16250","title":"AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding","created":"2025-12-18","cited_by_count":4,"area":"mllm"},{"id":"2602.11523","title":"Unifying Stable Optimization and Reference Regularization in RLHF","created":"2026-02-12","cited_by_count":4,"area":"alignment"},{"id":"2412.15256","title":"Structured Extraction of Real World Medical Knowledge using LLMs for Summarization and Search","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2501.14499","title":"Automated Assignment Grading with Large Language Models: Insights From a Bioinformatics Course","created":"2025-01-24","cited_by_count":3,"area":null},{"id":"2505.24768","title":"From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2508.03333","title":"CTTS: Collective Test-Time Scaling","created":"2025-08-05","cited_by_count":3,"area":"lr"},{"id":"2509.18901","title":"Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass","created":"2025-09-23","cited_by_count":3,"area":null},{"id":"2511.17937","title":"Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria","created":"2025-11-22","cited_by_count":3,"area":"alignment"},{"id":"2602.08829","title":"WildReward: Learning Reward Models from In-the-Wild Human Interactions","created":"2026-02-09","cited_by_count":3,"area":"alignment"},{"id":"2602.20670","title":"CAMEL: Confidence-Gated Reflection for Reward Modeling","created":"2026-02-24","cited_by_count":3,"area":"alignment"},{"id":"2604.13618","title":"C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences","created":"2026-04-15","cited_by_count":3,"area":"alignment"},{"id":"2502.17173","title":"Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch","created":"2025-02-24","cited_by_count":2,"area":"alignment"},{"id":"2503.16071","title":"Tuning LLMs by RAG Principles: Towards LLM-native Memory","created":"2025-03-20","cited_by_count":2,"area":"rag"},{"id":"2504.19594","title":"Mapping the Italian Telegram Ecosystem: Communities, Toxicity, and Hate Speech","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2509.23564","title":"Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment","created":"2025-09-28","cited_by_count":2,"area":"alignment"},{"id":"2601.01718","title":"Yuan3.0 Flash: An Open Multimodal Large Language Model for Enterprise Applications","created":"2026-01-05","cited_by_count":2,"area":"lr"},{"id":"2601.14032","title":"RM-Distiller: Exploiting Generative LLM for Reward Model Distillation","created":"2026-01-20","cited_by_count":2,"area":"alignment"},{"id":"2603.12795","title":"SteerRM: Debiasing Reward Models via Sparse Autoencoders","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2606.11762","title":"Automated Creativity Evaluation of Language Models Across Open-Ended Tasks","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2503.12686","title":"Understanding Formal Reasoning Failures in LLMs as Abstract Interpreters","created":"2025-03-16","cited_by_count":1,"area":"lr"},{"id":"2503.18908","title":"FFN Fusion: Rethinking Sequential Computation in Large Language Models","created":"2025-03-24","cited_by_count":1,"area":"lr"},{"id":"2504.12256","title":"FLIP Reasoning Challenge","created":"2025-04-16","cited_by_count":1,"area":"lr"},{"id":"2504.14177","title":"Direct Advantage Regression: Aligning LLMs with Online AI Reward","created":"2025-04-19","cited_by_count":1,"area":"alignment"},{"id":"2509.22851","title":"Adaptive Margin RLHF via Preference over Preferences","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2510.04087","title":"Best of mini-N in-loop Sampling: A Contextual Quality Reward Model for Reliable and Efficient Best-of-N Sampling","created":"2025-10-05","cited_by_count":1,"area":"alignment"},{"id":"2510.24446","title":"SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space","created":"2025-10-28","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}