{"list":"other","total":145,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"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":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2302.11382","title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","created":"2023-02-21","cited_by_count":619},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"1509.00685","title":"A Neural Attention Model for Abstractive Sentence Summarization","created":"2015-09-02","cited_by_count":396},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"1906.06127","title":"DocRED: A Large-Scale Document-Level Relation Extraction Dataset","created":"2019-06-14","cited_by_count":239},{"id":"1906.10742","title":"Machine Learning Testing: Survey, Landscapes and Horizons","created":"2019-06-19","cited_by_count":218},{"id":"2302.06527","title":"An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation","created":"2023-02-13","cited_by_count":194},{"id":"2310.03533","title":"Large Language Models for Software Engineering: Survey and Open Problems","created":"2023-10-05","cited_by_count":181},{"id":"2307.07221","title":"Software Testing with Large Language Models: Survey, Landscape, and Vision","created":"2023-07-14","cited_by_count":166},{"id":"2201.11227","title":"Synchromesh: Reliable code generation from pre-trained language models","created":"2022-01-26","cited_by_count":156},{"id":"2404.04834","title":"LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead","created":"2024-04-07","cited_by_count":155},{"id":"2205.10782","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","created":"2022-05-22","cited_by_count":152},{"id":"2009.07235","title":"Deep Learning based Vulnerability Detection: Are We There Yet?","created":"2020-09-03","cited_by_count":144},{"id":"2203.06566","title":"PromptChainer: Chaining Large Language Model Prompts through Visual Programming","created":"2022-03-13","cited_by_count":134},{"id":"2210.14179","title":"Practical Program Repair in the Era of Large Pre-trained Language Models","created":"2022-10-25","cited_by_count":133},{"id":"1903.10318","title":"Fine-tune BERT for Extractive Summarization","created":"2019-03-25","cited_by_count":122},{"id":"2309.05660","title":"Hypothesis Search: Inductive Reasoning with Language Models","created":"2023-09-11","cited_by_count":120},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119},{"id":"2009.05617","title":"Unit Test Case Generation with Transformers and Focal Context","created":"2020-09-11","cited_by_count":118},{"id":"2209.11515","title":"Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction","created":"2022-09-23","cited_by_count":111},{"id":"2212.06094","title":"Prompting Is Programming: A Query Language for Large Language Models","created":"2022-12-12","cited_by_count":110},{"id":"2212.14834","title":"Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models","created":"2022-12-30","cited_by_count":103},{"id":"2305.04764","title":"ChatUniTest: A Framework for LLM-Based Test Generation","created":"2023-05-08","cited_by_count":96},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92},{"id":"2203.15721","title":"On Decoding Strategies for Neural Text Generators","created":"2022-03-29","cited_by_count":90},{"id":"2308.04748","title":"Fuzz4All: Universal Fuzzing with Large Language Models","created":"2023-08-09","cited_by_count":88},{"id":"2305.15778","title":"Automatic Root Cause Analysis via Large Language Models for Cloud Incidents","created":"2023-05-25","cited_by_count":84},{"id":"2308.00121","title":"Getting pwn'd by AI: Penetration Testing with Large Language Models","created":"2023-07-24","cited_by_count":83},{"id":"2402.09171","title":"Automated Unit Test Improvement using Large Language Models at Meta","created":"2024-02-14","cited_by_count":75},{"id":"2402.09497","title":"Instruction Tuning for Secure Code Generation","created":"2024-02-14","cited_by_count":68},{"id":"2310.01726","title":"Large Language Models for Test-Free Fault Localization","created":"2023-10-03","cited_by_count":67},{"id":"2310.17807","title":"Clover: Closed-Loop Verifiable Code Generation","created":"2023-10-26","cited_by_count":67},{"id":"2308.03314","title":"GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis","created":"2023-08-07","cited_by_count":65},{"id":"2402.00097","title":"Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM","created":"2024-01-31","cited_by_count":64},{"id":"2403.04123","title":"Exploring LLM-based Agents for Root Cause Analysis","created":"2024-03-07","cited_by_count":61},{"id":"2311.16169","title":"Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities","created":"2023-11-16","cited_by_count":59},{"id":"2312.15223","title":"A Survey on Large Language Models for Software Engineering","created":"2023-12-23","cited_by_count":59},{"id":"2401.16185","title":"LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning","created":"2024-01-29","cited_by_count":59},{"id":"2402.00247","title":"Towards AI-Assisted Synthesis of Verified Dafny Methods","created":"2024-02-01","cited_by_count":58},{"id":"2404.00762","title":"Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification","created":"2024-03-31","cited_by_count":58},{"id":"2109.09262","title":"TOGA: A Neural Method for Test Oracle Generation","created":"2021-09-20","cited_by_count":57},{"id":"2310.01831","title":"Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?","created":"2023-10-03","cited_by_count":57},{"id":"2305.00418","title":"Using Large Language Models to Generate JUnit Tests: An Empirical Study","created":"2023-04-30","cited_by_count":53},{"id":"2401.08807","title":"SpecGen: Automated Generation of Formal Program Specifications via Large Language Models","created":"2024-01-16","cited_by_count":53},{"id":"2205.12424","title":"VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection","created":"2022-05-25","cited_by_count":51},{"id":"2308.12697","title":"Prompt-Enhanced Software Vulnerability Detection Using ChatGPT","created":"2023-08-24","cited_by_count":51},{"id":"2308.16557","title":"Effective Test Generation Using Pre-trained Large Language Models and Mutation Testing","created":"2023-08-31","cited_by_count":51},{"id":"2311.14479","title":"Controlled Text Generation via Language Model Arithmetic","created":"2023-11-24","cited_by_count":51},{"id":"2308.05487","title":"A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization","created":"2023-08-10","cited_by_count":50},{"id":"2305.11430","title":"TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Tasks","created":"2023-05-19","cited_by_count":49},{"id":"2310.04870","title":"Lemur: Integrating Large Language Models in Automated Program Verification","created":"2023-10-07","cited_by_count":49},{"id":"1812.02257","title":"On Testing Machine Learning Programs","created":"2018-12-05","cited_by_count":48},{"id":"2105.12378","title":"Anomaly Detection and Failure Root Cause Analysis in (Micro)Service-Based Cloud Applications: A Survey","created":"2021-05-26","cited_by_count":48},{"id":"2310.01152","title":"Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives","created":"2023-10-02","cited_by_count":48},{"id":"2310.12357","title":"Large Language Models for Code Analysis: Do LLMs Really Do Their Job?","created":"2023-10-18","cited_by_count":45},{"id":"2401.15468","title":"Large Language Model for Vulnerability Detection: Emerging Results and Future Directions","created":"2024-01-27","cited_by_count":45},{"id":"2310.09810","title":"ChatGPT for Vulnerability Detection, Classification, and Repair: How Far Are We?","created":"2023-10-15","cited_by_count":44},{"id":"2309.05520","title":"When ChatGPT Meets Smart Contract Vulnerability Detection: How Far Are We?","created":"2023-09-11","cited_by_count":42},{"id":"2404.02525","title":"Large Language Model for Vulnerability Detection and Repair: Literature Review and the Road Ahead","created":"2024-04-03","cited_by_count":42},{"id":"2305.14591","title":"ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers","created":"2023-05-24","cited_by_count":41},{"id":"2310.15780","title":"Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions","created":"2023-10-24","cited_by_count":41},{"id":"2304.02195","title":"Explainable Automated Debugging via Large Language Model-driven Scientific Debugging","created":"2023-04-05","cited_by_count":40},{"id":"2306.01987","title":"Prompting Is All You Need: Automated Android Bug Replay with Large Language Models","created":"2023-06-03","cited_by_count":40},{"id":"2206.01335","title":"Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Code","created":"2022-06-02","cited_by_count":39},{"id":"2311.08588","title":"CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation","created":"2023-11-14","cited_by_count":39},{"id":"2403.16218","title":"CoverUp: Effective High Coverage Test Generation for Python","created":"2024-03-24","cited_by_count":38},{"id":"2310.15991","title":"WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models","created":"2023-10-24","cited_by_count":37},{"id":"2206.05961","title":"A Survey on Automated Driving System Testing: Landscapes and Trends","created":"2022-06-13","cited_by_count":36},{"id":"2212.04732","title":"Fill in the Blank: Context-aware Automated Text Input Generation for Mobile GUI Testing","created":"2022-12-09","cited_by_count":36}],"next_cursor":"100"}