{"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/semantic-uncertainty-linguistic-invariances","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","arxiv_id":"2302.09664","date":"2023-02-19","proceeding":null,"authors":["Lorenz Kuhn","Yarin Gal","Sebastian Farquhar"],"abstract":"We introduce a method to measure uncertainty in large language models. For tasks like question answering, it is essential to know when we can trust the natural language outputs of foundation models. We show that measuring uncertainty in natural language is challenging because of \"semantic equivalence\" -- different sentences can mean the same thing. To overcome these challenges we introduce semantic entropy -- an entropy which incorporates linguistic invariances created by shared meanings. Our method is unsupervised, uses only a single model, and requires no modifications to off-the-shelf language models. In comprehensive ablation studies we show that the semantic entropy is more predictive of model accuracy on question answering data sets than comparable baselines.","url_abs":"https://arxiv.org/abs/2302.09664v3","url_pdf":"https://arxiv.org/pdf/2302.09664v3.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":"semantic-uncertainty-linguistic-invariances","repo_url":"https://github.com/lorenzkuhn/semantic_uncertainty","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"semantic-uncertainty-linguistic-invariances","repo_url":"https://github.com/ninodimontalcino/moralchoice","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"semantic-uncertainty-linguistic-invariances","repo_url":"https://github.com/iinemo/lm-polygraph","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.09664","atlas_url":"https://app.syntology.ai/?focus=2302.09664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.09664"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/lorenzkuhn/semantic_uncertainty","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ninodimontalcino/moralchoice","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"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":"707426419c228afb","entry":"get_log_likelihood_variance","repo":"lorenzkuhn/semantic_uncertainty","repo_kind":"official","path":"code/compute_confidence_measure.py","file_url":"https://github.com/lorenzkuhn/semantic_uncertainty/blob/HEAD/code/compute_confidence_measure.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"707426419c228afb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}