{"total":124,"rows":[{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988,"area":"lr"},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841,"area":null},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530,"area":"lr"},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452,"area":null},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384,"area":null},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323,"area":null},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2307.13528","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","created":"2023-07-25","cited_by_count":251,"area":null},{"id":"2406.01297","title":"When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs","created":"2024-06-03","cited_by_count":240,"area":null},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239,"area":"lr"},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238,"area":null},{"id":"2210.02875","title":"Binding Language Models in Symbolic Languages","created":"2022-10-06","cited_by_count":228,"area":null},{"id":"2311.17311","title":"Universal Self-Consistency for Large Language Model Generation","created":"2023-11-29","cited_by_count":203,"area":"lr"},{"id":"2306.09896","title":"Is Self-Repair a Silver Bullet for Code Generation?","created":"2023-06-16","cited_by_count":197,"area":null},{"id":"2504.07952","title":"Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory","created":"2025-04-10","cited_by_count":163,"area":null},{"id":"2309.11489","title":"Text2Reward: Reward Shaping with Language Models for Reinforcement Learning","created":"2023-09-20","cited_by_count":160,"area":"alignment"},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159,"area":null},{"id":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153,"area":null},{"id":"2302.05698","title":"Compositional Exemplars for In-context Learning","created":"2023-02-11","cited_by_count":144,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131,"area":null},{"id":"2402.16906","title":"Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step","created":"2024-02-25","cited_by_count":127,"area":null},{"id":"2406.08426","title":"Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL","created":"2024-06-12","cited_by_count":120,"area":null},{"id":"2305.04087","title":"Self-Edit: Fault-Aware Code Editor for Code Generation","created":"2023-05-06","cited_by_count":111,"area":null},{"id":"2209.15003","title":"Compositional Semantic Parsing with Large Language Models","created":"2022-09-29","cited_by_count":95,"area":null},{"id":"2211.16490","title":"Coder Reviewer Reranking for Code Generation","created":"2022-11-29","cited_by_count":84,"area":null},{"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,"area":"agents"},{"id":"2401.12869","title":"TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks","created":"2024-01-23","cited_by_count":75,"area":null},{"id":"2310.17807","title":"Clover: Closed-Loop Verifiable Code Generation","created":"2023-10-26","cited_by_count":67,"area":null},{"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,"area":null},{"id":"2211.07634","title":"Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding","created":"2022-11-14","cited_by_count":54,"area":null},{"id":"2310.01387","title":"It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk","created":"2023-10-02","cited_by_count":51,"area":null},{"id":"2411.04109","title":"Self-Consistency Preference Optimization","created":"2024-11-06","cited_by_count":50,"area":"lr"},{"id":"2309.17272","title":"Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency","created":"2023-09-29","cited_by_count":46,"area":"lr"},{"id":"2403.16792","title":"Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback","created":"2024-03-25","cited_by_count":46,"area":null},{"id":"2504.13139","title":"Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo","created":"2025-04-17","cited_by_count":46,"area":null},{"id":"2306.02907","title":"SelfEvolve: A Code Evolution Framework via Large Language Models","created":"2023-06-05","cited_by_count":43,"area":null},{"id":"2404.00725","title":"The Larger the Better? Improved LLM Code-Generation via Budget Reallocation","created":"2024-03-31","cited_by_count":43,"area":null},{"id":"2305.14591","title":"ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers","created":"2023-05-24","cited_by_count":41,"area":null},{"id":"2311.14919","title":"Faster Minimum Bayes Risk Decoding with Confidence-based Pruning","created":"2023-11-25","cited_by_count":34,"area":null},{"id":"2411.04329","title":"CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models","created":"2024-11-07","cited_by_count":34,"area":"lr"},{"id":"2503.15341","title":"Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs","created":"2025-03-19","cited_by_count":32,"area":"lr"},{"id":"2302.10166","title":"Learning Deep Semantics for Test Completion","created":"2023-02-20","cited_by_count":31,"area":null},{"id":"2406.12053","title":"InternalInspector $I^2$: Robust Confidence Estimation in LLMs through Internal States","created":"2024-06-17","cited_by_count":30,"area":null},{"id":"2308.08784","title":"CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation","created":"2023-08-17","cited_by_count":29,"area":"lr"},{"id":"2410.08105","title":"What Makes Large Language Models Reason in (Multi-Turn) Code Generation?","created":"2024-10-10","cited_by_count":29,"area":"lr"},{"id":"2309.17446","title":"L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models","created":"2023-09-29","cited_by_count":22,"area":null},{"id":"2402.12317","title":"EVOR: Evolving Retrieval for Code Generation","created":"2024-02-19","cited_by_count":22,"area":"rag"},{"id":"2409.05001","title":"A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement","created":"2024-09-08","cited_by_count":21,"area":null},{"id":"2504.05410","title":"Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2308.06261","title":"Enhancing Network Management Using Code Generated by Large Language Models","created":"2023-08-11","cited_by_count":20,"area":null},{"id":"2501.10858","title":"Reliable Text-to-SQL with Adaptive Abstention","created":"2025-01-18","cited_by_count":20,"area":null},{"id":"2502.11741","title":"SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL","created":"2025-02-17","cited_by_count":19,"area":"synth"},{"id":"2311.09868","title":"INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair","created":"2023-11-16","cited_by_count":18,"area":null},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18,"area":null},{"id":"2408.15533","title":"LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation","created":"2024-08-28","cited_by_count":17,"area":"rag"},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2502.10802","title":"CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2407.15343","title":"Improving Minimum Bayes Risk Decoding with Multi-Prompt","created":"2024-07-22","cited_by_count":13,"area":null},{"id":"2305.13917","title":"Generating Data for Symbolic Language with Large Language Models","created":"2023-05-23","cited_by_count":12,"area":null},{"id":"2210.00848","title":"Toward Trustworthy Neural Program Synthesis","created":"2022-09-29","cited_by_count":11,"area":null},{"id":"2305.01598","title":"From Words to Code: Harnessing Data for Program Synthesis from Natural Language","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2310.05727","title":"The Program Testing Ability of Large Language Models for Code","created":"2023-10-09","cited_by_count":11,"area":null},{"id":"2303.00732","title":"R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents","created":"2023-03-01","cited_by_count":10,"area":null},{"id":"2307.06857","title":"Lightweight reranking for language model generations","created":"2023-07-11","cited_by_count":10,"area":null},{"id":"2405.13131","title":"Atomic Self-Consistency for Better Long Form Generations","created":"2024-05-21","cited_by_count":10,"area":"lr"},{"id":"2311.03366","title":"Functional Overlap Reranking for Neural Code Generation","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2402.13284","title":"Structure Guided Large Language Model for SQL Generation","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2407.10456","title":"Don't Throw Away Data: Better Sequence Knowledge Distillation","created":"2024-07-15","cited_by_count":9,"area":"distill"},{"id":"2409.08692","title":"B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests","created":"2024-09-13","cited_by_count":9,"area":null},{"id":"2404.14453","title":"EPI-SQL: Enhancing Text-to-SQL Translation with Error-Prevention Instructions","created":"2024-04-21","cited_by_count":8,"area":null},{"id":"2405.19581","title":"Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2407.02518","title":"INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness","created":"2024-06-23","cited_by_count":8,"area":null},{"id":"2408.00994","title":"ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models","created":"2024-08-02","cited_by_count":8,"area":null},{"id":"2410.01556","title":"Integrative Decoding: Improve Factuality via Implicit Self-consistency","created":"2024-10-02","cited_by_count":8,"area":"lr"},{"id":"2402.08073","title":"Grounding Data Science Code Generation with Input-Output Specifications","created":"2024-02-12","cited_by_count":7,"area":null},{"id":"2411.14503","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","created":"2024-11-21","cited_by_count":7,"area":null},{"id":"2501.01668","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","created":"2025-01-03","cited_by_count":7,"area":"lr"},{"id":"2602.04254","title":"Scaling Agentic Verifier for Competitive Coding","created":"2026-02-04","cited_by_count":7,"area":"agents"},{"id":"2603.05863","title":"ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2310.01717","title":"Ensemble Distillation for Unsupervised Constituency Parsing","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2305.09438","title":"MPI-rical: Data-Driven MPI Distributed Parallelism Assistance with Transformers","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2506.18403","title":"The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs","created":"2025-06-23","cited_by_count":5,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2408.13745","title":"DOCE: Finding the Sweet Spot for Execution-Based Code Generation","created":"2024-08-25","cited_by_count":4,"area":null},{"id":"2409.07131","title":"Reranking Laws for Language Generation: A Communication-Theoretic Perspective","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2509.17393","title":"Program Synthesis via Test-Time Transduction","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2603.12932","title":"DS$^2$-Instruct: Domain-Specific Data Synthesis for Large Language Models Instruction Tuning","created":"2026-03-13","cited_by_count":4,"area":"synth"},{"id":"2409.13551","title":"Contextualized Data-Wrangling Code Generation in Computational Notebooks","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2502.09589","title":"Logical forms complement probability in understanding language model (and human) performance","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2505.24716","title":"Towards Scalable Schema Mapping using Large Language Models","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2508.00255","title":"Accurate and Consistent Graph Model Generation from Text with Large Language Models","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2508.01237","title":"SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches","created":"2025-08-02","cited_by_count":3,"area":null},{"id":"2510.00591","title":"AI-Driven Self-Evolving Software: A Promising Path Toward Software Automation","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2602.06098","title":"A Theoretical Analysis of Test-Driven Code Generation","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2604.17501","title":"CoAct: Co-Active LLM Preference Learning with Human-AI Synergy","created":"2026-04-19","cited_by_count":3,"area":"alignment"},{"id":"2208.11523","title":"Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer","created":"2022-08-24","cited_by_count":2,"area":null}],"next_cursor":"100"}