{"list":"other","total":53,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2212.10509","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","created":"2022-12-20","cited_by_count":923},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"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":"2402.07927","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","created":"2024-02-05","cited_by_count":431},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331},{"id":"2311.09210","title":"Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models","created":"2023-11-15","cited_by_count":184},{"id":"1805.08949","title":"Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow","created":"2018-05-23","cited_by_count":165},{"id":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153},{"id":"2011.09926","title":"Challenges in Deploying Machine Learning: a Survey of Case Studies","created":"2020-11-18","cited_by_count":152},{"id":"2307.11760","title":"Large Language Models Understand and Can be Enhanced by Emotional Stimuli","created":"2023-07-14","cited_by_count":146},{"id":"2309.12499","title":"CodePlan: Repository-level Coding using LLMs and Planning","created":"2023-09-21","cited_by_count":140},{"id":"2203.07722","title":"ReACC: A Retrieval-Augmented Code Completion Framework","created":"2022-03-15","cited_by_count":119},{"id":"2206.12839","title":"Repository-Level Prompt Generation for Large Language Models of Code","created":"2022-06-26","cited_by_count":106},{"id":"2404.08189","title":"Reducing hallucination in structured outputs via Retrieval-Augmented Generation","created":"2024-04-12","cited_by_count":93},{"id":"2406.14497","title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","created":"2024-06-20","cited_by_count":91},{"id":"1910.11015","title":"Taxonomy of Real Faults in Deep Learning Systems","created":"2019-10-24","cited_by_count":90},{"id":"2206.06888","title":"CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation","created":"2022-06-14","cited_by_count":87},{"id":"2407.01219","title":"Searching for Best Practices in Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":83},{"id":"2403.10446","title":"Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases","created":"2024-03-15","cited_by_count":77},{"id":"1906.01388","title":"A Comprehensive Study on Deep Learning Bug Characteristics","created":"2019-06-03","cited_by_count":65},{"id":"2110.10234","title":"Collaboration Challenges in Building ML-Enabled Systems: Communication, Documentation, Engineering, and Process","created":"2021-10-19","cited_by_count":56},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","cited_by_count":49},{"id":"2407.12994","title":"A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks","created":"2024-07-17","cited_by_count":47},{"id":"2302.06144","title":"SkCoder: A Sketch-based Approach for Automatic Code Generation","created":"2023-02-13","cited_by_count":40},{"id":"2406.07003","title":"GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model","created":"2024-06-11","cited_by_count":40},{"id":"2401.13256","title":"UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems","created":"2024-01-24","cited_by_count":38},{"id":"2407.07064","title":"Prompting Techniques for Secure Code Generation: A Systematic Investigation","created":"2024-07-09","cited_by_count":34},{"id":"2007.14130","title":"Adoption and Effects of Software Engineering Best Practices in Machine Learning","created":"2020-07-28","cited_by_count":33},{"id":"2402.17497","title":"REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering","created":"2024-02-27","cited_by_count":28},{"id":"2203.04026","title":"Toward Understanding Deep Learning Framework Bugs","created":"2022-03-08","cited_by_count":26},{"id":"2101.04930","title":"An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applications","created":"2021-01-13","cited_by_count":20},{"id":"2308.09313","title":"Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases","created":"2023-08-18","cited_by_count":19},{"id":"2206.12311","title":"Bugs in Machine Learning-based Systems: A Faultload Benchmark","created":"2022-06-24","cited_by_count":15},{"id":"2407.05138","title":"Are LLMs Correctly Integrated into Software Systems?","created":"2024-07-06","cited_by_count":15},{"id":"2112.01771","title":"Understanding Performance Problems in Deep Learning Systems","created":"2021-12-03","cited_by_count":12},{"id":"2102.06919","title":"Asset Management in Machine Learning: A Survey","created":"2021-02-13","cited_by_count":7},{"id":"2408.06226","title":"A Large-Scale Study of Model Integration in ML-Enabled Software Systems","created":"2024-08-12","cited_by_count":6}],"next_cursor":null}