{"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/aligning-instruction-tasks-unlocks-large","title":"Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors","arxiv_id":"2305.11159","date":"2023-05-18","proceeding":null,"authors":["Kai Zhang","Bernal Jiménez Gutiérrez","Yu Su"],"abstract":"Recent work has shown that fine-tuning large language models (LLMs) on large-scale instruction-following datasets substantially improves their performance on a wide range of NLP tasks, especially in the zero-shot setting. However, even advanced instruction-tuned LLMs still fail to outperform small LMs on relation extraction (RE), a fundamental information extraction task. We hypothesize that instruction-tuning has been unable to elicit strong RE capabilities in LLMs due to RE's low incidence in instruction-tuning datasets, making up less than 1% of all tasks (Wang et al., 2022). To address this limitation, we propose QA4RE, a framework that aligns RE with question answering (QA), a predominant task in instruction-tuning datasets. Comprehensive zero-shot RE experiments over four datasets with two series of instruction-tuned LLMs (six LLMs in total) demonstrate that our QA4RE framework consistently improves LLM performance, strongly verifying our hypothesis and enabling LLMs to outperform strong zero-shot baselines by a large margin. Additionally, we provide thorough experiments and discussions to show the robustness, few-shot effectiveness, and strong transferability of our QA4RE framework. This work illustrates a promising way of adapting LLMs to challenging and underrepresented tasks by aligning these tasks with more common instruction-tuning tasks like QA.","url_abs":"https://arxiv.org/abs/2305.11159v1","url_pdf":"https://arxiv.org/pdf/2305.11159v1.pdf","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":[{"paper_slug":"aligning-instruction-tasks-unlocks-large","repo_url":"https://github.com/osu-nlp-group/qa4re","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[{"method_slug":"fail","method_name":"fail"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-re-tacred","task":"Relation Extraction","dataset":"Re-TACRED","model":"LLM-QA4RE (XXLarge)","rank_in_archive_order":9,"of":9,"metrics":{"F1":"66.5"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-semeval-2010-task-8-1","task":"Relation Extraction","dataset":"SemEval-2010 Task 8","model":"LLM-QA4RE (XXLarge)","rank_in_archive_order":1,"of":2,"metrics":{"F1":"43.5"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-tacred","task":"Relation Extraction","dataset":"TACRED","model":"LLM-QA4RE (XXLarge)","rank_in_archive_order":39,"of":40,"metrics":{"F1":"52.2"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-tacred-revisited","task":"Relation Extraction","dataset":"TACRED-Revisited","model":"LLM-QA4RE (XXLarge)","rank_in_archive_order":3,"of":3,"metrics":{"F1":"53.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.11159","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}