{"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/improving-open-information-extraction-with","title":"Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty","arxiv_id":"2309.03433","date":"2023-09-07","proceeding":null,"authors":["Chen Ling","Xujiang Zhao","Xuchao Zhang","Yanchi Liu","Wei Cheng","Haoyu Wang","Zhengzhang Chen","Takao Osaki","Katsushi Matsuda","Haifeng Chen","Liang Zhao"],"abstract":"Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text, typically in the form of (subject, relation, object) triples. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks due to two key issues. First, LLMs struggle to distinguish irrelevant context from relevant relations and generate structured output due to the restrictions on fine-tuning the model. Second, LLMs generates responses autoregressively based on probability, which makes the predicted relations lack confidence. In this paper, we assess the capabilities of LLMs in improving the OIE task. Particularly, we propose various in-context learning strategies to enhance LLM's instruction-following ability and a demonstration uncertainty quantification module to enhance the confidence of the generated relations. Our experiments on three OIE benchmark datasets show that our approach holds its own against established supervised methods, both quantitatively and qualitatively.","url_abs":"https://arxiv.org/abs/2309.03433v1","url_pdf":"https://arxiv.org/pdf/2309.03433v1.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":[],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"open-information-extraction","task_name":"Open Information Extraction"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-information-extraction-on-carb","task":"Open Information Extraction","dataset":"CaRB","model":"GPT-3.5-Turbo w/ Selected Demo & Uncertainty","rank_in_archive_order":9,"of":29,"metrics":{"F1":"52.1"},"uses_additional_data":false},{"leaderboard":"/sota/open-information-extraction-on-carb","task":"Open Information Extraction","dataset":"CaRB","model":"LLaMA-2-70B w/ Selected Demo & Uncertainty","rank_in_archive_order":12,"of":29,"metrics":{"F1":"51.5"},"uses_additional_data":false},{"leaderboard":"/sota/open-information-extraction-on-carb","task":"Open Information Extraction","dataset":"CaRB","model":"LLaMA-2-13B w/ Selected Demo & Uncertainty","rank_in_archive_order":26,"of":29,"metrics":{"F1":"36.2"},"uses_additional_data":false},{"leaderboard":"/sota/open-information-extraction-on-oie2016","task":"Open Information Extraction","dataset":"OIE2016","model":"LLaMA-2-70B w/ Selected Demo & Uncertainty","rank_in_archive_order":6,"of":12,"metrics":{"F1":"65.8"},"uses_additional_data":false},{"leaderboard":"/sota/open-information-extraction-on-oie2016","task":"Open Information Extraction","dataset":"OIE2016","model":"GPT-3.5-Turbo w/ Selected Demo & Uncertainty","rank_in_archive_order":7,"of":12,"metrics":{"F1":"65.1"},"uses_additional_data":false},{"leaderboard":"/sota/open-information-extraction-on-oie2016","task":"Open Information Extraction","dataset":"OIE2016","model":"LLaMA-2-13B w/ Selected Demo & Uncertainty","rank_in_archive_order":11,"of":12,"metrics":{"F1":"36.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.03433","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}