{"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-uncertainty-quantification","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","arxiv_id":"2406.15627","date":"2024-06-21","proceeding":null,"authors":["Roman Vashurin","Ekaterina Fadeeva","Artem Vazhentsev","Lyudmila Rvanova","Akim Tsvigun","Daniil Vasilev","Rui Xing","Abdelrahman Boda Sadallah","Kirill Grishchenkov","Sergey Petrakov","Alexander Panchenko","Timothy Baldwin","Preslav Nakov","Maxim Panov","Artem Shelmanov"],"abstract":"The rapid proliferation of large language models (LLMs) has stimulated researchers to seek effective and efficient approaches to deal with LLM hallucinations and low-quality outputs. Uncertainty quantification (UQ) is a key element of machine learning applications in dealing with such challenges. However, research to date on UQ for LLMs has been fragmented in terms of techniques and evaluation methodologies. In this work, we address this issue by introducing a novel benchmark that implements a collection of state-of-the-art UQ baselines and offers an environment for controllable and consistent evaluation of novel UQ techniques over various text generation tasks. Our benchmark also supports the assessment of confidence normalization methods in terms of their ability to provide interpretable scores. Using our benchmark, we conduct a large-scale empirical investigation of UQ and normalization techniques across eleven tasks, identifying the most effective approaches. Code: https://github.com/IINemo/lm-polygraph Benchmark: https://huggingface.co/LM-Polygraph","url_abs":"https://arxiv.org/abs/2406.15627v3","url_pdf":"https://arxiv.org/pdf/2406.15627v3.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-uncertainty-quantification","repo_url":"https://github.com/iinemo/lm-polygraph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"benchmarking-uncertainty-quantification","repo_url":"https://github.com/jinhaoduan/sar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"benchmarking-uncertainty-quantification","repo_url":"https://github.com/jinhaoduan/shifting-attention-to-relevance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.15627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15627"}},"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/iinemo/lm-polygraph","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jinhaoduan/sar","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jinhaoduan/shifting-attention-to-relevance","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"unverified":2},"by_repo_kind":{"listed":{"samples":4,"ran":2,"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":"baf52bd8c74211f8","entry":"sar","repo":"jinhaoduan/shifting-attention-to-relevance","repo_kind":"listed","path":"src/compute_uncertainty.py","file_url":"https://github.com/jinhaoduan/shifting-attention-to-relevance/blob/HEAD/src/compute_uncertainty.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"baf52bd8c74211f8"}},{"code_sha256_prefix":"9ec4f3a16dcdb560","entry":"sentence_sar","repo":"jinhaoduan/shifting-attention-to-relevance","repo_kind":"listed","path":"src/compute_uncertainty.py","file_url":"https://github.com/jinhaoduan/shifting-attention-to-relevance/blob/HEAD/src/compute_uncertainty.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9ec4f3a16dcdb560"}},{"code_sha256_prefix":"f21d9ce0471b640a","entry":"get_neg_loglikelihoods","repo":"jinhaoduan/shifting-attention-to-relevance","repo_kind":"listed","path":"src/get_likelihoods.py","file_url":"https://github.com/jinhaoduan/shifting-attention-to-relevance/blob/HEAD/src/get_likelihoods.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":"f21d9ce0471b640a"}},{"code_sha256_prefix":"eb882324991f4da4","entry":"get_token_wise_entropies","repo":"jinhaoduan/shifting-attention-to-relevance","repo_kind":"listed","path":"src/get_likelihoods.py","file_url":"https://github.com/jinhaoduan/shifting-attention-to-relevance/blob/HEAD/src/get_likelihoods.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":"eb882324991f4da4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}