{"list":"other","total":55,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"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":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2108.09293","title":"Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions","created":"2021-08-20","cited_by_count":431},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278},{"id":"2211.00053","title":"Generating Sequences by Learning to Self-Correct","created":"2022-10-31","cited_by_count":277},{"id":"2105.12655","title":"CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks","created":"2021-05-25","cited_by_count":200},{"id":"2211.03622","title":"Do Users Write More Insecure Code with AI Assistants?","created":"2022-11-07","cited_by_count":192},{"id":"2302.05319","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","created":"2023-02-10","cited_by_count":155},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151},{"id":"2312.04724","title":"Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models","created":"2023-12-07","cited_by_count":138},{"id":"2206.12839","title":"Repository-Level Prompt Generation for Large Language Models of Code","created":"2022-06-26","cited_by_count":106},{"id":"2302.07867","title":"Learning Performance-Improving Code Edits","created":"2023-02-15","cited_by_count":106},{"id":"2306.14111","title":"Is RLHF More Difficult than Standard RL?","created":"2023-06-25","cited_by_count":96},{"id":"2210.15157","title":"Conversing with Copilot: Exploring Prompt Engineering for Solving CS1 Problems Using Natural Language","created":"2022-10-27","cited_by_count":82},{"id":"2311.08596","title":"Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment","created":"2023-11-14","cited_by_count":77},{"id":"2402.01391","title":"StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback","created":"2024-02-02","cited_by_count":77},{"id":"2303.07839","title":"ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design","created":"2023-03-11","cited_by_count":66},{"id":"2303.09384","title":"LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluations","created":"2023-03-16","cited_by_count":62},{"id":"2404.00725","title":"The Larger the Better? Improved LLM Code-Generation via Budget Reallocation","created":"2024-03-31","cited_by_count":43},{"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":"2401.15963","title":"NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness","created":"2024-01-29","cited_by_count":26},{"id":"2404.18864","title":"Performance-Aligned LLMs for Generating Fast Code","created":"2024-04-29","cited_by_count":21},{"id":"2208.14613","title":"How Readable is Model-generated Code? Examining Readability and Visual Inspection of GitHub Copilot","created":"2022-08-31","cited_by_count":14},{"id":"2206.13619","title":"DeepPERF: A Deep Learning-Based Approach For Improving Software Performance","created":"2022-06-27","cited_by_count":6},{"id":"1904.01754","title":"Styler: learning formatting conventions to repair Checkstyle violations","created":"2019-04-03","cited_by_count":3}],"next_cursor":null}