{"total":120,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459,"area":"lr"},{"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":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374,"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":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332,"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":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988,"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":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664,"area":"lr"},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652,"area":"lr"},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625,"area":"lr"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388,"area":"lr"},{"id":"2305.00050","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","created":"2023-04-28","cited_by_count":353,"area":"lr"},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346,"area":"lr"},{"id":"2604.13016","title":"Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe","created":"2026-04-14","cited_by_count":299,"area":"lr"},{"id":"2310.05492","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","created":"2023-10-09","cited_by_count":223,"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":"2210.03849","title":"ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering","created":"2022-10-07","cited_by_count":196,"area":"lr"},{"id":"2305.07004","title":"Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting","created":"2023-05-11","cited_by_count":165,"area":"lr"},{"id":"2205.00445","title":"MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning","created":"2022-05-01","cited_by_count":156,"area":"lr"},{"id":"2310.03731","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","created":"2023-10-05","cited_by_count":156,"area":"lr"},{"id":"2405.03548","title":"MAmmoTH2: Scaling Instructions from the Web","created":"2024-05-06","cited_by_count":145,"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":"2304.02015","title":"How well do Large Language Models perform in Arithmetic tasks?","created":"2023-03-16","cited_by_count":130,"area":"lr"},{"id":"2209.07686","title":"Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango","created":"2022-09-16","cited_by_count":128,"area":"lr"},{"id":"2508.05629","title":"On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification","created":"2025-08-07","cited_by_count":127,"area":"lr"},{"id":"2306.03872","title":"Deductive Verification of Chain-of-Thought Reasoning","created":"2023-06-06","cited_by_count":124,"area":"lr"},{"id":"2210.06710","title":"Large Language Models are few(1)-shot Table Reasoners","created":"2022-10-13","cited_by_count":116,"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":"2305.09656","title":"SatLM: Satisfiability-Aided Language Models Using Declarative Prompting","created":"2023-05-16","cited_by_count":102,"area":"lr"},{"id":"2210.05359","title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","created":"2022-10-11","cited_by_count":84,"area":"lr"},{"id":"2210.16257","title":"Solving Math Word Problems via Cooperative Reasoning induced Language Models","created":"2022-10-28","cited_by_count":77,"area":"lr"},{"id":"2305.13412","title":"Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method","created":"2023-05-22","cited_by_count":76,"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":"2503.24370","title":"Effectively Controlling Reasoning Models through Thinking Intervention","created":"2025-03-31","cited_by_count":65,"area":"lr"},{"id":"2305.14825","title":"Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners","created":"2023-05-24","cited_by_count":63,"area":"lr"},{"id":"2501.17703","title":"Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate","created":"2025-01-29","cited_by_count":63,"area":"lr"},{"id":"2310.04959","title":"Towards Better Chain-of-Thought Prompting Strategies: A Survey","created":"2023-10-08","cited_by_count":62,"area":"lr"},{"id":"2302.00618","title":"Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models","created":"2023-02-01","cited_by_count":61,"area":"lr"},{"id":"2212.01326","title":"Legal Prompting: Teaching a Language Model to Think Like a Lawyer","created":"2022-12-02","cited_by_count":60,"area":"lr"},{"id":"2303.00293","title":"How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks","created":"2023-03-01","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":"2511.06449","title":"FLEX: Continuous Agent Evolution via Forward Learning from Experience","created":"2025-11-09","cited_by_count":52,"area":"lr"},{"id":"2406.08527","title":"Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning","created":"2024-06-12","cited_by_count":49,"area":"lr"},{"id":"2305.14497","title":"Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement","created":"2023-05-23","cited_by_count":43,"area":"lr"},{"id":"2503.17523","title":"Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models","created":"2025-03-21","cited_by_count":37,"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":"2404.14963","title":"Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems","created":"2024-04-23","cited_by_count":31,"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":"2605.07804","title":"Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning","created":"2026-05-08","cited_by_count":27,"area":"lr"},{"id":"2412.00383","title":"Unified Parameter-Efficient Unlearning for LLMs","created":"2024-11-30","cited_by_count":25,"area":"lr"},{"id":"2301.10896","title":"Causal Reasoning of Entities and Events in Procedural Texts","created":"2023-01-26","cited_by_count":23,"area":"lr"},{"id":"2301.11596","title":"ThoughtSource: A central hub for large language model reasoning data","created":"2023-01-27","cited_by_count":23,"area":"lr"},{"id":"2205.12598","title":"RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning","created":"2022-05-25","cited_by_count":22,"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":"2310.05057","title":"BRAINTEASER: Lateral Thinking Puzzles for Large Language Models","created":"2023-10-08","cited_by_count":18,"area":"lr"},{"id":"2501.16207","title":"From Informal to Formal -- Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs","created":"2025-01-27","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":"2307.07951","title":"MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning","created":"2023-07-16","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":"2310.19019","title":"TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise","created":"2023-10-29","cited_by_count":15,"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":"2210.08590","title":"Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective","created":"2022-10-16","cited_by_count":14,"area":"lr"},{"id":"2210.12338","title":"Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge","created":"2022-10-22","cited_by_count":14,"area":"lr"},{"id":"2310.05030","title":"Counter Turing Test CT^2: AI-Generated Text Detection is Not as Easy as You May Think -- Introducing AI Detectability Index","created":"2023-10-08","cited_by_count":14,"area":"lr"},{"id":"2405.17057","title":"ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation","created":"2024-05-27","cited_by_count":14,"area":"lr"},{"id":"2210.17517","title":"Lila: A Unified Benchmark for Mathematical Reasoning","created":"2022-10-31","cited_by_count":13,"area":"lr"},{"id":"2402.16631","title":"GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning","created":"2024-02-26","cited_by_count":13,"area":"lr"},{"id":"2406.17642","title":"Banishing LLM Hallucinations Requires Rethinking Generalization","created":"2024-06-25","cited_by_count":13,"area":"lr"},{"id":"2303.03628","title":"CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification","created":"2023-03-07","cited_by_count":11,"area":"lr"},{"id":"2310.06692","title":"Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models","created":"2023-10-10","cited_by_count":11,"area":"lr"},{"id":"2508.19277","title":"POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization","created":"2025-08-23","cited_by_count":11,"area":"lr"},{"id":"2507.14783","title":"Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling","created":"2025-07-20","cited_by_count":10,"area":"lr"},{"id":"2403.19962","title":"Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning","created":"2024-03-29","cited_by_count":9,"area":"lr"},{"id":"2403.09085","title":"Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance","created":"2024-03-14","cited_by_count":8,"area":"lr"},{"id":"2404.12728","title":"Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?","created":"2024-04-19","cited_by_count":8,"area":"lr"},{"id":"2505.21354","title":"Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoning","created":"2025-05-27","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":"2401.05787","title":"Chain of Evidences and Evidence to Generate: Prompting for Context Grounded and Retrieval Augmented Reasoning","created":"2024-01-11","cited_by_count":7,"area":"lr"},{"id":"2404.03028","title":"An Incomplete Loop: Deductive, Inductive, and Abductive Reasoning in Language Models","created":"2024-04-03","cited_by_count":7,"area":"lr"},{"id":"2410.11900","title":"FLARE: Faithful Logic-Aided Reasoning and Exploration","created":"2024-10-14","cited_by_count":7,"area":"lr"},{"id":"2305.06841","title":"Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models","created":"2023-05-11","cited_by_count":6,"area":"lr"},{"id":"2305.14457","title":"Pre-training Language Models for Comparative Reasoning","created":"2023-05-23","cited_by_count":6,"area":"lr"},{"id":"2404.16068","title":"SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense","created":"2024-04-22","cited_by_count":6,"area":"lr"},{"id":"2601.04897","title":"V-FAT: Benchmarking Visual Fidelity Against Text-bias","created":"2026-01-08","cited_by_count":6,"area":"lr"},{"id":"2501.16884","title":"Irony Detection, Reasoning and Understanding in Zero-shot Learning","created":"2025-01-28","cited_by_count":5,"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":"2306.02258","title":"Probing Physical Reasoning with Counter-Commonsense Context","created":"2023-06-04","cited_by_count":4,"area":"lr"},{"id":"2310.05442","title":"Establishing Trustworthiness: Rethinking Tasks and Model Evaluation","created":"2023-10-09","cited_by_count":4,"area":"lr"},{"id":"2312.17532","title":"Enhancing Quantitative Reasoning Skills of Large Language Models through Dimension Perception","created":"2023-12-29","cited_by_count":4,"area":"lr"},{"id":"2502.19409","title":"ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models","created":"2025-02-26","cited_by_count":4,"area":"lr"},{"id":"2505.17217","title":"Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs","created":"2025-05-22","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":"2510.07048","title":"Search-R3: Unifying Reasoning and Embedding in Large Language Models","created":"2025-10-08","cited_by_count":4,"area":"lr"},{"id":"2210.11265","title":"Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers","created":"2022-10-20","cited_by_count":3,"area":"lr"},{"id":"2305.17491","title":"FERMAT: An Alternative to Accuracy for Numerical Reasoning","created":"2023-05-27","cited_by_count":3,"area":"lr"},{"id":"2504.01324","title":"On Data Synthesis and Post-training for Visual Abstract Reasoning","created":"2025-04-02","cited_by_count":3,"area":"lr"}],"next_cursor":"100"}