{"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/benchmarking-llms-via-uncertainty","title":"Benchmarking LLMs via Uncertainty Quantification","arxiv_id":"2401.12794","date":"2024-01-23","proceeding":null,"authors":["Fanghua Ye","Mingming Yang","Jianhui Pang","Longyue Wang","Derek F. Wong","Emine Yilmaz","Shuming Shi","Zhaopeng Tu"],"abstract":"The proliferation of open-source Large Language Models (LLMs) from various institutions has highlighted the urgent need for comprehensive evaluation methods. However, current evaluation platforms, such as the widely recognized HuggingFace open LLM leaderboard, neglect a crucial aspect -- uncertainty, which is vital for thoroughly assessing LLMs. To bridge this gap, we introduce a new benchmarking approach for LLMs that integrates uncertainty quantification. Our examination involves nine LLMs (LLM series) spanning five representative natural language processing tasks. Our findings reveal that: I) LLMs with higher accuracy may exhibit lower certainty; II) Larger-scale LLMs may display greater uncertainty compared to their smaller counterparts; and III) Instruction-finetuning tends to increase the uncertainty of LLMs. These results underscore the significance of incorporating uncertainty in the evaluation of LLMs.","url_abs":"https://arxiv.org/abs/2401.12794v3","url_pdf":"https://arxiv.org/pdf/2401.12794v3.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":"benchmarking-llms-via-uncertainty","repo_url":"https://github.com/smartyfh/llm-uncertainty-bench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.12794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12794"}},"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":"deterministic:regex_extraction","url":"https://github.com/smartyfh/LLM-Uncertainty-Bench","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/smartyfh/llm-uncertainty-bench","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":7,"ran_violates":1,"ran":5,"unverified":4},"by_repo_kind":{"official":{"samples":16,"ran":12,"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":1,"samples":[{"code_sha256_prefix":"9cb5a160cb942951","entry":"load_data","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"generate_logits.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/generate_logits.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9cb5a160cb942951"}},{"code_sha256_prefix":"7f9b15275ca5759c","entry":"softmax","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"7f9b15275ca5759c"}},{"code_sha256_prefix":"1a38d8124050f460","entry":"cal_acc","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a38d8124050f460"}},{"code_sha256_prefix":"2d8b9343c19529f9","entry":"cal_coverage","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d8b9343c19529f9"}},{"code_sha256_prefix":"b53afba9c0da9944","entry":"cal_set_size","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b53afba9c0da9944"}},{"code_sha256_prefix":"50a4b22e789fd992","entry":"cal_uacc","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50a4b22e789fd992"}},{"code_sha256_prefix":"037e99602ccc4435","entry":"convert_id_to_ans","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"037e99602ccc4435"}},{"code_sha256_prefix":"7027200b9089953e","entry":"get_accuracy","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7027200b9089953e"}},{"code_sha256_prefix":"50b7e2a98d17a3d4","entry":"get_fewshot_exps","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"generate_logits.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/generate_logits.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50b7e2a98d17a3d4"}},{"code_sha256_prefix":"fc79c5e7f5428533","entry":"get_logits_data","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc79c5e7f5428533"}},{"code_sha256_prefix":"d27097c4a183befa","entry":"get_logits_data","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d27097c4a183befa"}},{"code_sha256_prefix":"756bbcda282e506a","entry":"get_raw_data","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"756bbcda282e506a"}},{"code_sha256_prefix":"f1da4e31dbe5407b","entry":"get_raw_data","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1da4e31dbe5407b"}},{"code_sha256_prefix":"6fc15eb0d745506b","entry":"APS_CP","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.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":"6fc15eb0d745506b"}},{"code_sha256_prefix":"8f79d57c0ec1f93b","entry":"LAC_CP","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.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":"8f79d57c0ec1f93b"}},{"code_sha256_prefix":"051cab8f58895ebd","entry":"apply_conformal_prediction","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.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":"051cab8f58895ebd"}},{"code_sha256_prefix":"ae9771b6b08aedbd","entry":"softmax","repo":"smartyfh/llm-uncertainty-bench","repo_kind":"official","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae9771b6b08aedbd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}