{"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/prudent-silence-or-foolish-babble-examining","title":"Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge","arxiv_id":"2311.09731","date":"2023-11-16","proceeding":null,"authors":["Genglin Liu","Xingyao Wang","Lifan Yuan","Yangyi Chen","Hao Peng"],"abstract":"Can large language models (LLMs) express their uncertainty in situations where they lack sufficient parametric knowledge to generate reasonable responses? This work aims to systematically investigate LLMs' behaviors in such situations, emphasizing the trade-off between honesty and helpfulness. To tackle the challenge of precisely determining LLMs' knowledge gaps, we diagnostically create unanswerable questions containing non-existent concepts or false premises, ensuring that they are outside the LLMs' vast training data. By compiling a benchmark, UnknownBench, which consists of both unanswerable and answerable questions, we quantitatively evaluate the LLMs' performance in maintaining honesty while being helpful. Using a model-agnostic unified confidence elicitation approach, we observe that most LLMs fail to consistently refuse or express uncertainty towards questions outside their parametric knowledge, although instruction fine-tuning and alignment techniques can provide marginal enhancements. Moreover, LLMs' uncertainty expression does not always stay consistent with the perceived confidence of their textual outputs.","url_abs":"https://arxiv.org/abs/2311.09731v2","url_pdf":"https://arxiv.org/pdf/2311.09731v2.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":"prudent-silence-or-foolish-babble-examining","repo_url":"https://github.com/genglinliu/unknownbench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.09731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09731"}},"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/genglinliu/unknownbench","reach":{"status":"ok"}}],"summary":{"ran":7,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"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":9,"samples":[{"code_sha256_prefix":"453e41ef783e7fe4","entry":"get_acc_vs_rating","repo":"genglinliu/unknownbench","repo_kind":"official","path":"src/external_evaluation_of_responses_with_chatgpt.py","file_url":"https://github.com/genglinliu/unknownbench/blob/HEAD/src/external_evaluation_of_responses_with_chatgpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"453e41ef783e7fe4"}},{"code_sha256_prefix":"cfa6311203dffb9f","entry":"get_existing_samples_in_output_file","repo":"genglinliu/unknownbench","repo_kind":"official","path":"src/external_evaluation_of_responses_with_chatgpt.py","file_url":"https://github.com/genglinliu/unknownbench/blob/HEAD/src/external_evaluation_of_responses_with_chatgpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cfa6311203dffb9f"}},{"code_sha256_prefix":"7d61d401b8ebd5c8","entry":"get_existing_samples_in_output_file","repo":"genglinliu/unknownbench","repo_kind":"official","path":"src/run_llama_and_vicuna.py","file_url":"https://github.com/genglinliu/unknownbench/blob/HEAD/src/run_llama_and_vicuna.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d61d401b8ebd5c8"}},{"code_sha256_prefix":"992922d3939d5ed0","entry":"get_existing_samples_in_output_file","repo":"genglinliu/unknownbench","repo_kind":"official","path":"src/run_proprietary_LLMs.py","file_url":"https://github.com/genglinliu/unknownbench/blob/HEAD/src/run_proprietary_LLMs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"992922d3939d5ed0"}},{"code_sha256_prefix":"5da5cbdc6a11455a","entry":"get_paths","repo":"genglinliu/unknownbench","repo_kind":"official","path":"src/run_mistral.py","file_url":"https://github.com/genglinliu/unknownbench/blob/HEAD/src/run_mistral.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5da5cbdc6a11455a"}},{"code_sha256_prefix":"1328167b94bcaec9","entry":"get_paths","repo":"genglinliu/unknownbench","repo_kind":"official","path":"src/unified_verbalized_confidence_regression.py","file_url":"https://github.com/genglinliu/unknownbench/blob/HEAD/src/unified_verbalized_confidence_regression.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1328167b94bcaec9"}},{"code_sha256_prefix":"9e266763140afec2","entry":"load_model","repo":"genglinliu/unknownbench","repo_kind":"official","path":"src/run_llama_and_vicuna.py","file_url":"https://github.com/genglinliu/unknownbench/blob/HEAD/src/run_llama_and_vicuna.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e266763140afec2"}},{"code_sha256_prefix":"ff08724afec72f1d","entry":"get_paths","repo":"genglinliu/unknownbench","repo_kind":"official","path":"src/run_llama_and_vicuna.py","file_url":"https://github.com/genglinliu/unknownbench/blob/HEAD/src/run_llama_and_vicuna.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff08724afec72f1d"}},{"code_sha256_prefix":"d4fb89b496c43b4c","entry":"run_mistral_via_openai","repo":"genglinliu/unknownbench","repo_kind":"official","path":"src/run_mistral.py","file_url":"https://github.com/genglinliu/unknownbench/blob/HEAD/src/run_mistral.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d4fb89b496c43b4c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}