{"total":53,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065,"area":"lr"},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919,"area":"lr"},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807,"area":"lr"},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434,"area":"lr"},{"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":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688,"area":"lr"},{"id":"2307.02477","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","created":"2023-07-05","cited_by_count":246,"area":"lr"},{"id":"2303.09014","title":"ART: Automatic multi-step reasoning and tool-use for large language models","created":"2023-03-16","cited_by_count":197,"area":"lr"},{"id":"2207.07051","title":"Language models show human-like content effects on reasoning tasks","created":"2022-07-14","cited_by_count":173,"area":"lr"},{"id":"2403.04642","title":"Teaching Large Language Models to Reason with Reinforcement Learning","created":"2024-03-07","cited_by_count":160,"area":"lr"},{"id":"2310.06117","title":"Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models","created":"2023-10-09","cited_by_count":159,"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":"2402.03620","title":"Self-Discover: Large Language Models Self-Compose Reasoning Structures","created":"2024-02-06","cited_by_count":110,"area":"lr"},{"id":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108,"area":"lr"},{"id":"2310.01714","title":"Large Language Models as Analogical Reasoners","created":"2023-10-03","cited_by_count":107,"area":"lr"},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71,"area":"lr"},{"id":"2404.15522","title":"LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models","created":"2024-04-23","cited_by_count":68,"area":"lr"},{"id":"2310.05707","title":"Guiding Language Model Reasoning with Planning Tokens","created":"2023-10-09","cited_by_count":58,"area":"lr"},{"id":"2310.15166","title":"Large Language Models are Visual Reasoning Coordinators","created":"2023-10-23","cited_by_count":58,"area":"lr"},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2410.06458","title":"LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints","created":"2024-10-09","cited_by_count":35,"area":"lr"},{"id":"2507.23751","title":"CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks","created":"2025-07-31","cited_by_count":32,"area":"lr"},{"id":"2305.17878","title":"Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models","created":"2023-05-29","cited_by_count":31,"area":"lr"},{"id":"2410.23743","title":"What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective","created":"2024-10-31","cited_by_count":29,"area":"lr"},{"id":"2301.00355","title":"Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits","created":"2023-01-01","cited_by_count":27,"area":"lr"},{"id":"2310.11716","title":"Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning","created":"2023-10-18","cited_by_count":26,"area":"lr"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2208.08232","title":"HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with Models","created":"2022-08-17","cited_by_count":17,"area":"lr"},{"id":"2212.08286","title":"ALERT: Adapting Language Models to Reasoning Tasks","created":"2022-12-16","cited_by_count":17,"area":"lr"},{"id":"2402.13459","title":"Learning to Poison Large Language Models for Downstream Manipulation","created":"2024-02-21","cited_by_count":16,"area":"lr"},{"id":"2504.20708","title":"Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think","created":"2025-04-29","cited_by_count":16,"area":"lr"},{"id":"2509.13351","title":"Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning","created":"2025-09-14","cited_by_count":15,"area":"lr"},{"id":"2210.17517","title":"Lila: A Unified Benchmark for Mathematical Reasoning","created":"2022-10-31","cited_by_count":13,"area":"lr"},{"id":"2310.09430","title":"Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning","created":"2023-10-13","cited_by_count":10,"area":"lr"},{"id":"2402.12091","title":"Do Large Language Models Understand Logic or Just Mimick Context?","created":"2024-02-19","cited_by_count":10,"area":"lr"},{"id":"2409.11724","title":"TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning","created":"2024-09-18","cited_by_count":10,"area":"lr"},{"id":"2510.04230","title":"Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2505.14412","title":"PRL: Prompts from Reinforcement Learning","created":"2025-05-20","cited_by_count":9,"area":"lr"},{"id":"2509.14662","title":"Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory","created":"2025-09-18","cited_by_count":9,"area":"lr"},{"id":"2510.03595","title":"Decoupling Task-Solving and Output Formatting in LLM Generation","created":"2025-10-04","cited_by_count":9,"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":"2410.06733","title":"Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation Puzzles","created":"2024-10-09","cited_by_count":8,"area":"lr"},{"id":"2212.01692","title":"Can In-context Learners Learn a Reasoning Concept from Demonstrations?","created":"2022-12-03","cited_by_count":7,"area":"lr"},{"id":"2402.10543","title":"Strong hallucinations from negation and how to fix them","created":"2024-02-16","cited_by_count":6,"area":"lr"},{"id":"2211.03252","title":"Zero-Shot Classification by Logical Reasoning on Natural Language Explanations","created":"2022-11-07","cited_by_count":4,"area":"lr"},{"id":"2409.18996","title":"From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models","created":"2024-09-19","cited_by_count":4,"area":"lr"},{"id":"2501.10688","title":"Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers","created":"2025-01-18","cited_by_count":4,"area":"lr"},{"id":"2508.03018","title":"Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning","created":"2025-08-05","cited_by_count":4,"area":"lr"},{"id":"2309.10444","title":"Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models","created":"2023-09-19","cited_by_count":3,"area":"lr"},{"id":"2603.02239","title":"Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents","created":"2026-02-16","cited_by_count":2,"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":"2605.22902","title":"Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2610.04072","title":"Reinforcement Learning with Comparative Evidence for Social Intelligence","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}