{"total":61,"rows":[{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708,"area":"lr"},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462,"area":"lr"},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"area":"lr"},{"id":"2202.04053","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","created":"2022-02-08","cited_by_count":230,"area":"lr"},{"id":"2311.18651","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","created":"2023-11-30","cited_by_count":210,"area":"lr"},{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210,"area":"lr"},{"id":"2305.00633","title":"Self-Evaluation Guided Beam Search for Reasoning","created":"2023-05-01","cited_by_count":196,"area":"lr"},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2307.15337","title":"Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation","created":"2023-07-28","cited_by_count":105,"area":"lr"},{"id":"2309.09117","title":"Contrastive Decoding Improves Reasoning in Large Language Models","created":"2023-09-17","cited_by_count":74,"area":"lr"},{"id":"2305.13091","title":"Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization","created":"2023-05-22","cited_by_count":70,"area":"lr"},{"id":"2503.01422","title":"Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding","created":"2025-03-03","cited_by_count":63,"area":"lr"},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2504.12522","title":"Evaluating the Diversity and Quality of LLM Generated Content","created":"2025-04-16","cited_by_count":51,"area":"lr"},{"id":"2307.02768","title":"Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts","created":"2023-07-06","cited_by_count":31,"area":"lr"},{"id":"2512.12895","title":"Wait, Wait, Wait... Why Do Reasoning Models Loop?","created":"2025-12-15","cited_by_count":26,"area":"lr"},{"id":"2401.17686","title":"Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning","created":"2024-01-31","cited_by_count":24,"area":"lr"},{"id":"2306.07932","title":"Human-in-the-Loop through Chain-of-Thought","created":"2023-06-10","cited_by_count":20,"area":"lr"},{"id":"2203.07285","title":"Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts","created":"2022-03-14","cited_by_count":19,"area":"lr"},{"id":"2404.16807","title":"Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning","created":"2024-04-25","cited_by_count":19,"area":"lr"},{"id":"2403.07872","title":"Rethinking Generative Large Language Model Evaluation for Semantic Comprehension","created":"2024-03-12","cited_by_count":13,"area":"lr"},{"id":"2305.04530","title":"A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues","created":"2023-05-08","cited_by_count":11,"area":"lr"},{"id":"2310.06374","title":"Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Models","created":"2023-10-10","cited_by_count":8,"area":"lr"},{"id":"2602.11683","title":"ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces","created":"2026-02-12","cited_by_count":8,"area":"lr"},{"id":"2311.09325","title":"Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the \"right reasons\"?","created":"2023-11-15","cited_by_count":7,"area":"lr"},{"id":"2601.09609","title":"DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing","created":"2026-01-14","cited_by_count":6,"area":"lr"},{"id":"2505.18071","title":"Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals","created":"2025-05-23","cited_by_count":5,"area":"lr"},{"id":"2510.13940","title":"Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention","created":"2025-10-15","cited_by_count":5,"area":"lr"},{"id":"2511.07922","title":"SERL: Self-Examining Reinforcement Learning on Open-Domain","created":"2025-11-11","cited_by_count":5,"area":"lr"},{"id":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2602.01698","title":"Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2602.04208","title":"SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2305.14434","title":"Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction","created":"2023-05-23","cited_by_count":3,"area":"lr"},{"id":"2601.22629","title":"Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2602.20094","title":"CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching","created":"2026-02-23","cited_by_count":3,"area":"lr"},{"id":"2405.10251","title":"A Systematic Evaluation of Large Language Models for Natural Language Generation Tasks","created":"2024-05-16","cited_by_count":2,"area":"lr"},{"id":"2508.06046","title":"EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation","created":"2025-08-08","cited_by_count":2,"area":"lr"},{"id":"2508.18763","title":"Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units","created":"2025-08-26","cited_by_count":2,"area":"lr"},{"id":"2510.09599","title":"Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation","created":"2025-10-10","cited_by_count":2,"area":"lr"},{"id":"2512.13262","title":"Post-Training and Test-Time Scaling of Generative Agent Behavior Models for Interactive Autonomous Driving","created":"2025-12-15","cited_by_count":2,"area":"lr"},{"id":"2501.01872","title":"Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions","created":"2025-01-03","cited_by_count":1,"area":"lr"},{"id":"2503.17136","title":"CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization","created":"2025-03-21","cited_by_count":1,"area":"lr"},{"id":"2601.01714","title":"Entropy-Aligned Decoding of LMs for Better Writing and Reasoning","created":"2026-01-05","cited_by_count":1,"area":"lr"},{"id":"2601.21619","title":"On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2601.22536","title":"Decoding in Geometry: Alleviating Embedding-Space Crowding for Complex Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2604.20500","title":"Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2502.11751","title":"Language Models Can See Better: Visual Contrastive Decoding For LLM Multimodal Reasoning","created":"2025-02-17","cited_by_count":0,"area":"lr"},{"id":"2503.01819","title":"Do GFlowNets Transfer? Case Study on the Game of 24/42","created":"2025-03-03","cited_by_count":0,"area":"lr"},{"id":"2509.01308","title":"GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models","created":"2025-09-01","cited_by_count":0,"area":"lr"},{"id":"2510.14763","title":"COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes","created":"2025-10-16","cited_by_count":0,"area":"lr"},{"id":"2512.05747","title":"Capturing Classic Authorial Style in Long-Form Story Generation with GRPO Fine-Tuning","created":"2025-12-05","cited_by_count":0,"area":"lr"},{"id":"2601.03606","title":"Policy-Guided Search on Tree-of-Thoughts for Efficient Problem Solving with Bounded Language Model Queries","created":"2026-01-07","cited_by_count":0,"area":"lr"},{"id":"2601.12212","title":"Speculative Sampling with Reinforcement Learning","created":"2026-01-18","cited_by_count":0,"area":"lr"},{"id":"2603.14745","title":"CAMD: Coverage-Aware Multimodal Decoding for Efficient Reasoning of Multimodal Large Language Models","created":"2026-03-16","cited_by_count":0,"area":"lr"},{"id":"2604.10502","title":"CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2604.10504","title":"CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2606.17524","title":"Learning to Refine Hidden States for Reliable LLM Reasoning","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2609.33585","title":"IVT-Guard: All-in-One Reasoning Model for AI-Generated Content Detection","created":"2026-09-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}