{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fine-tuning-large-language-models-for","title":"Fine-Tuning Large Language Models for Answering Programming Questions with Code Snippets","arxiv_id":null,"date":"2023-06-26","proceeding":"ICCS: International Conference on Computational Science 2023 6","authors":["Vadim Lomshakov","Sergey Kovalchuk","Maxim Omelchenko","Sergey Nikolenko","Artem Aliev"],"abstract":"We study the ability of pretrained large language models (LLM) to answer questions from online question answering fora such as Stack Overflow. We consider question-answer pairs where the main part of the answer consists of source code. On two benchmark datasets—CoNaLa and a newly collected dataset based on Stack Overflow—we investigate how a closed-book question answering system can be improved by fine-tuning the LLM for the downstream task, prompt engineering, and data preprocessing. We use publicly available autoregressive language models such as GPT-Neo, CodeGen, and PanGu-Coder, and after the proposed fine-tuning achieve a BLEU score of 0.4432 on the CoNaLa test set, significantly exceeding previous state of the art for this task.","url_abs":"https://link.springer.com/chapter/10.1007/978-3-031-36021-3_15","url_pdf":"https://link.springer.com/chapter/10.1007/978-3-031-36021-3_15","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"program-synthesis","task_name":"Program Synthesis"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-to-code-generation","task_name":"Text-to-Code Generation"}],"methods":[{"method_slug":"codegen","method_name":"CodeGen"},{"method_slug":"gpt-neo","method_name":"GPT-Neo"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-conala","task":"Code Generation","dataset":"CoNaLa","model":"PanGu-Coder-FT-I","rank_in_archive_order":1,"of":14,"metrics":{"BLEU":"44.32"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}