{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:34:25Z","timestamp":1780054465597,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671445","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"6416-6417","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Domain-Driven LLM Development: Insights into RAG and Fine-Tuning Practices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3224-5029","authenticated-orcid":false,"given":"Jos\u00e9 Cassio","family":"dos Santos Junior","sequence":"first","affiliation":[{"name":"Amazon Web Services, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1339-4475","authenticated-orcid":false,"given":"Rachel","family":"Hu","sequence":"additional","affiliation":[{"name":"CambioML Corp, San Jose, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6854-6372","authenticated-orcid":false,"given":"Richard","family":"Song","sequence":"additional","affiliation":[{"name":"Epsilla, Jersey City, New Jersey, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0270-6123","authenticated-orcid":false,"given":"Yunfei","family":"Bai","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel Sebastian Riedel Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv:2005.11401 [cs.LG]"},{"key":"e_1_3_2_1_2_1","volume-title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval. arXiv:2401.18059 [cs.LG]","author":"Sarthi Parth","year":"2024","unstructured":"Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Ann Goldie, Christopher D. Manning. 2024. RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval. arXiv:2401.18059 [cs.LG]"},{"key":"e_1_3_2_1_3_1","volume-title":"REPLUG: Retrieval-Augmented Black-Box Language Models. arXiv:2301.12652 [cs.LG]","author":"Shi Weijia","year":"2023","unstructured":"Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Rich James, Mike Lewis, Luke Zettlemoyer, Wen-tau Yih. 2023. REPLUG: Retrieval-Augmented Black-Box Language Models. arXiv:2301.12652 [cs.LG]"},{"key":"e_1_3_2_1_4_1","volume-title":"Promptagator: Few-shot Dense Retrieval From 8 Examples. arXiv: 2209.11755 [cs.LG]","author":"Dai Zhuyun","year":"2022","unstructured":"Zhuyun Dai, Vincent Y. Zhao, Ji Ma, Yi Luan, Jianmo Ni, Jing Lu, Anton Bakalov, Kelvin Guu, Keith B. Hall, Ming-Wei Chang. 2022. Promptagator: Few-shot Dense Retrieval From 8 Examples. arXiv: 2209.11755 [cs.LG]"},{"key":"e_1_3_2_1_5_1","volume-title":"Ankita Rajaram Naik, Pengshan Cai, Alfio Gliozzo.","author":"Glass Michael","year":"2022","unstructured":"Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Ankita Rajaram Naik, Pengshan Cai, Alfio Gliozzo. 2022. Re2G: Retrieve, Rerank, Generate. arXiv: 2207.06300 [cs.LG]"},{"key":"e_1_3_2_1_6_1","volume-title":"XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing. arXiv: 2210.13693 [cs.LG]","author":"Shi Peng","year":"2022","unstructured":"Peng Shi, Rui Zhang, He Bai, Jimmy Lin. 2022. XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing. arXiv: 2210.13693 [cs.LG]"},{"key":"e_1_3_2_1_7_1","volume-title":"Llmlingua: Compressing prompts for accelerated inference of large language models. arXiv: 2310.05736 [cs.LG]","author":"Jiang Huiqiang","year":"2023","unstructured":"Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, Lili Qiu. 2023. Llmlingua: Compressing prompts for accelerated inference of large language models. arXiv: 2310.05736 [cs.LG]"},{"key":"e_1_3_2_1_8_1","volume-title":"Quoc V Le, Denny Zhou.","author":"Zheng Huaixiu Steven","year":"2023","unstructured":"Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen, Heng-Tze Cheng, Ed H. Chi, Quoc V Le, Denny Zhou. 2023. Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models. arXiv: 2310.06117 [cs.LG]"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Liang Wang Nan Yang Furu Wei. 2023. Query2doc: Query Expansion with Large Language Models. arXiv: 2303.07678 [cs.LG]","DOI":"10.18653\/v1\/2023.emnlp-main.585"},{"key":"e_1_3_2_1_10_1","unstructured":"Xinbei Ma Yeyun Gong Pengcheng He Hai Zhao Nan Duan. 2023. Query Rewriting for Retrieval-Augmented Large Language Models. arXiv: 2305.14283 [cs.LG]"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Luyu Gao Xueguang Ma Jimmy Lin Jamie Callan. 2022. Precise Zero-Shot Dense Retrieval without Relevance Labels. arXiv: 2212.10496 [cs.LG]","DOI":"10.18653\/v1\/2023.acl-long.99"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Zackary Rackauckas. 2024. RAG-Fusion: a New Take on Retrieval-Augmented Generation. arXiv: 2402.03367 [cs.LG]","DOI":"10.5121\/ijnlc.2024.13103"},{"key":"e_1_3_2_1_13_1","volume-title":"Zhengxiao Du, Zhilin Yang, Jie Tang.","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Lam Tam, Zhengxiao Du, Zhilin Yang, Jie Tang. 2021. P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks. arXiv: 2110.07602 [cs.LG]"},{"key":"e_1_3_2_1_14_1","unstructured":"Angels Balaguer Vinamra Benara Renato Cunha Roberto Estev\u00e3o Todd Hendry Daniel Holstein Jennifer Marsman Nick Mecklenburg Sara Malvar Leonardo O. Nunes Rafael Padilha Morris Sharp Bruno Silva Swati Sharma Vijay Aski Ranveer Chandra. 2024. RAG vs Fine-tuning: Pipelines Tradeoffs and a Case Study on Agriculture. arXiv: 2401.08406 [cs.LG]"},{"key":"e_1_3_2_1_15_1","unstructured":"Heydar Soudani Evangelos Kanoulas Faegheh Hasibi. 2024. Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge. arXiv: 2403.01432 [cs.LG]"},{"key":"e_1_3_2_1_16_1","unstructured":"Oded Ovadia Menachem Brief Moshik Mishaeli Oren Elisha. 2024. Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs. arXiv: 2312.05934 [cs.LG]"},{"key":"e_1_3_2_1_17_1","unstructured":"Shamane Siriwardhana Rivindu Weerasekera Elliott Wen Suranga Nanayakkara. 2021. Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering. arXiv: 2106.11517 [cs.LG]"},{"key":"e_1_3_2_1_18_1","volume-title":"RAFT: Adapting Language Model to Domain Specific RAG. arXiv: 2403.10131 [cs.LG]","author":"Zhang Tianjun","year":"2024","unstructured":"Tianjun Zhang, Shishir G. Patil, Naman Jain, Sheng Shen, Matei Zaharia, Ion Stoica, Joseph E. Gonzalez. 2024. RAFT: Adapting Language Model to Domain Specific RAG. arXiv: 2403.10131 [cs.LG]"},{"key":"e_1_3_2_1_19_1","unstructured":"Shicheng Xu Liang Pang Mo Yu Fandong Meng Huawei Shen Xueqi Cheng Jie Zhou. 2024. Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation. arXiv: 2402.18150 [cs.LG]"},{"key":"e_1_3_2_1_20_1","unstructured":"Mandar Kulkarni Praveen Tangarajan Kyung Kim Anusua Trivedi. 2024. Reinforcement Learning for Optimizing RAG for Domain Chatbots. arXiv: 2401.06800 [cs.LG]"}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671445","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:25Z","timestamp":1750291405000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671445"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":20,"alternative-id":["10.1145\/3637528.3671445","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671445","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}