{"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/knowledge-of-knowledge-exploring-known","title":"Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models","arxiv_id":"2305.13712","date":"2023-05-23","proceeding":null,"authors":["Alfonso Amayuelas","Kyle Wong","Liangming Pan","Wenhu Chen","William Wang"],"abstract":"This paper investigates the capabilities of Large Language Models (LLMs) in the context of understanding their knowledge and uncertainty over questions. Specifically, we focus on addressing known-unknown questions, characterized by high uncertainty due to the absence of definitive answers. To facilitate our study, we collect a new dataset with Known-Unknown Questions (KUQ) and establish a categorization framework to clarify the origins of uncertainty in such queries. Subsequently, we examine the performance of open-source LLMs, fine-tuned using this dataset, in distinguishing between known and unknown queries within open-ended question-answering scenarios. The fine-tuned models demonstrated a significant improvement, achieving a considerable increase in F1-score relative to their pre-fine-tuning state. Through a comprehensive analysis, we reveal insights into the models' improved uncertainty articulation and their consequent efficacy in multi-agent debates. These findings help us understand how LLMs can be trained to identify and express uncertainty, improving our knowledge of how they understand and express complex or unclear information.","url_abs":"https://arxiv.org/abs/2305.13712v3","url_pdf":"https://arxiv.org/pdf/2305.13712v3.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":"knowledge-of-knowledge-exploring-known","repo_url":"https://github.com/amayuelas/knowledge-of-knowledge","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"known-unknowns","task_name":"Known Unknowns"},{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.13712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13712"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amayuelas/knowledge-of-knowledge","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"df081be962c9166d","entry":"cut_sentences","repo":"amayuelas/knowledge-of-knowledge","repo_kind":"official","path":"evaluate_template.py","file_url":"https://github.com/amayuelas/knowledge-of-knowledge/blob/HEAD/evaluate_template.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df081be962c9166d"}},{"code_sha256_prefix":"0eaaedec6ce15969","entry":"cut_sub_string","repo":"amayuelas/knowledge-of-knowledge","repo_kind":"official","path":"evaluate_template.py","file_url":"https://github.com/amayuelas/knowledge-of-knowledge/blob/HEAD/evaluate_template.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0eaaedec6ce15969"}},{"code_sha256_prefix":"1c182cddb8d32031","entry":"format_AmbigQA","repo":"amayuelas/knowledge-of-knowledge","repo_kind":"official","path":"format_datasets.py","file_url":"https://github.com/amayuelas/knowledge-of-knowledge/blob/HEAD/format_datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c182cddb8d32031"}},{"code_sha256_prefix":"02eef9d4d55f7060","entry":"format_FalseQA","repo":"amayuelas/knowledge-of-knowledge","repo_kind":"official","path":"format_datasets.py","file_url":"https://github.com/amayuelas/knowledge-of-knowledge/blob/HEAD/format_datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"02eef9d4d55f7060"}},{"code_sha256_prefix":"b6f7401f562f9fb2","entry":"format_qaqa","repo":"amayuelas/knowledge-of-knowledge","repo_kind":"official","path":"format_datasets.py","file_url":"https://github.com/amayuelas/knowledge-of-knowledge/blob/HEAD/format_datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6f7401f562f9fb2"}},{"code_sha256_prefix":"caa9fadfd3d87408","entry":"load_llama_model","repo":"amayuelas/knowledge-of-knowledge","repo_kind":"official","path":"run_model.py","file_url":"https://github.com/amayuelas/knowledge-of-knowledge/blob/HEAD/run_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"caa9fadfd3d87408"}},{"code_sha256_prefix":"6ead2c3000b10c17","entry":"template_check","repo":"amayuelas/knowledge-of-knowledge","repo_kind":"official","path":"evaluate_template.py","file_url":"https://github.com/amayuelas/knowledge-of-knowledge/blob/HEAD/evaluate_template.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ead2c3000b10c17"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}