{"list":"other","total":110,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421},{"id":"2202.13169","title":"A Systematic Evaluation of Large Language Models of Code","created":"2022-02-26","cited_by_count":363},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353},{"id":"2406.11931","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","created":"2024-06-17","cited_by_count":331},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300},{"id":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278},{"id":"2304.07590","title":"Self-collaboration Code Generation via ChatGPT","created":"2023-04-15","cited_by_count":258},{"id":"2207.14255","title":"Efficient Training of Language Models to Fill in the Middle","created":"2022-07-28","cited_by_count":255},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238},{"id":"2002.04326","title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","created":"2020-02-11","cited_by_count":217},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203},{"id":"2311.04939","title":"LooGLE: Can Long-Context Language Models Understand Long Contexts?","created":"2023-11-08","cited_by_count":202},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189},{"id":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183},{"id":"2210.07128","title":"Language Models of Code are Few-Shot Commonsense Learners","created":"2022-10-13","cited_by_count":160},{"id":"2310.03731","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","created":"2023-10-05","cited_by_count":156},{"id":"2308.06259","title":"Self-Alignment with Instruction Backtranslation","created":"2023-08-11","cited_by_count":151},{"id":"2402.14830","title":"Orca-Math: Unlocking the potential of SLMs in Grade School Math","created":"2024-02-16","cited_by_count":151},{"id":"2406.11409","title":"CodeGemma: Open Code Models Based on Gemma","created":"2024-06-17","cited_by_count":150},{"id":"2309.12499","title":"CodePlan: Repository-level Coding using LLMs and Planning","created":"2023-09-21","cited_by_count":140},{"id":"2303.06689","title":"Self-planning Code Generation with Large Language Models","created":"2023-03-12","cited_by_count":124},{"id":"2410.05983","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","created":"2024-10-08","cited_by_count":123},{"id":"2306.14893","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","created":"2023-06-26","cited_by_count":112},{"id":"2305.04087","title":"Self-Edit: Fault-Aware Code Editor for Code Generation","created":"2023-05-06","cited_by_count":111},{"id":"2306.16636","title":"CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?","created":"2023-06-29","cited_by_count":90},{"id":"2411.07781","title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","created":"2024-11-12","cited_by_count":90},{"id":"2409.03733","title":"Planning In Natural Language Improves LLM Search For Code Generation","created":"2024-09-05","cited_by_count":83},{"id":"2309.16298","title":"At Which Training Stage Does Code Data Help LLMs Reasoning?","created":"2023-09-28","cited_by_count":82},{"id":"2401.08190","title":"MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline","created":"2024-01-16","cited_by_count":81},{"id":"2401.00812","title":"If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents","created":"2024-01-01","cited_by_count":79},{"id":"2406.20098","title":"Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs","created":"2024-06-28","cited_by_count":74},{"id":"2007.08124","title":"LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning","created":"2020-07-16","cited_by_count":69},{"id":"2402.09880","title":"Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence","created":"2024-02-15","cited_by_count":68},{"id":"2403.04811","title":"Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models","created":"2024-03-06","cited_by_count":65},{"id":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61},{"id":"2009.11506","title":"Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems","created":"2020-09-24","cited_by_count":60},{"id":"2310.08992","title":"CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules","created":"2023-10-13","cited_by_count":58},{"id":"2401.02582","title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","created":"2024-01-05","cited_by_count":56},{"id":"2409.01666","title":"In Defense of RAG in the Era of Long-Context Language Models","created":"2024-09-03","cited_by_count":53},{"id":"2409.02076","title":"LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs","created":"2024-09-03","cited_by_count":47},{"id":"2403.19114","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","created":"2024-03-28","cited_by_count":40},{"id":"2410.08196","title":"MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code","created":"2024-10-10","cited_by_count":39},{"id":"2312.13010","title":"AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation","created":"2023-12-20","cited_by_count":35},{"id":"2406.06025","title":"RepoQA: Evaluating Long Context Code Understanding","created":"2024-06-10","cited_by_count":35},{"id":"2405.20535","title":"Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning","created":"2024-05-30","cited_by_count":31},{"id":"2109.08365","title":"CodeQA: A Question Answering Dataset for Source Code Comprehension","created":"2021-09-17","cited_by_count":30},{"id":"2305.10314","title":"LeTI: Learning to Generate from Textual Interactions","created":"2023-05-17","cited_by_count":25},{"id":"2409.12452","title":"Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning","created":"2024-09-19","cited_by_count":25},{"id":"2401.10065","title":"Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs","created":"2024-01-18","cited_by_count":20},{"id":"2410.12468","title":"Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios","created":"2024-10-16","cited_by_count":18},{"id":"2309.16120","title":"Fixing Large Language Models' Specification Misunderstanding for Better Code Generation","created":"2023-09-28","cited_by_count":17},{"id":"2305.18507","title":"Code Prompting: a Neural Symbolic Method for Complex Reasoning in Large Language Models","created":"2023-05-29","cited_by_count":16},{"id":"2406.04604","title":"Learning Task Decomposition to Assist Humans in Competitive Programming","created":"2024-06-07","cited_by_count":14},{"id":"2311.13258","title":"ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation","created":"2023-11-22","cited_by_count":13},{"id":"2406.13764","title":"Can LLMs Reason in the Wild with Programs?","created":"2024-06-19","cited_by_count":13},{"id":"2408.13533","title":"Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models","created":"2024-08-24","cited_by_count":13},{"id":"2409.19381","title":"HYBRIDMIND: Meta Selection of Natural Language and Symbolic Language for Enhanced LLM Reasoning","created":"2024-09-28","cited_by_count":11},{"id":"2410.02229","title":"CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning","created":"2024-10-03","cited_by_count":10},{"id":"2403.02567","title":"Eliciting Better Multilingual Structured Reasoning from LLMs through Code","created":"2024-03-05","cited_by_count":9},{"id":"2410.05255","title":"Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization","created":"2024-10-07","cited_by_count":9},{"id":"2407.16974","title":"SelfPiCo: Self-Guided Partial Code Execution with LLMs","created":"2024-07-24","cited_by_count":7},{"id":"2411.13826","title":"Interactive and Expressive Code-Augmented Planning with Large Language Models","created":"2024-11-21","cited_by_count":7},{"id":"2411.14503","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","created":"2024-11-21","cited_by_count":7}],"next_cursor":"100"}