{"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/uqlm-a-python-package-for-uncertainty","title":"UQLM: A Python Package for Uncertainty Quantification in Large Language Models","arxiv_id":"2507.06196","date":"2025-07-08","proceeding":null,"authors":["Dylan Bouchard","Mohit Singh Chauhan","David Skarbrevik","Ho-Kyeong Ra","Viren Bajaj","Zeya Ahmad"],"abstract":"Hallucinations, defined as instances where Large Language Models (LLMs) generate false or misleading content, pose a significant challenge that impacts the safety and trust of downstream applications. We introduce UQLM, a Python package for LLM hallucination detection using state-of-the-art uncertainty quantification (UQ) techniques. This toolkit offers a suite of UQ-based scorers that compute response-level confidence scores ranging from 0 to 1. This library provides an off-the-shelf solution for UQ-based hallucination detection that can be easily integrated to enhance the reliability of LLM outputs.","url_abs":"https://arxiv.org/abs/2507.06196v1","url_pdf":"https://arxiv.org/pdf/2507.06196v1.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":"uqlm-a-python-package-for-uncertainty","repo_url":"https://github.com/cvs-health/uqlm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2507.06196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06196"}},"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/cvs-health/uqlm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"ec88955355e0aa69","entry":"clean_if_name","repo":"cvs-health/uqlm","repo_kind":"official","path":"uqlm/code/lcb_grader.py","file_url":"https://github.com/cvs-health/uqlm/blob/HEAD/uqlm/code/lcb_grader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec88955355e0aa69"}},{"code_sha256_prefix":"60cdbbe10c98b7ab","entry":"evaluate_python_code","repo":"cvs-health/uqlm","repo_kind":"official","path":"uqlm/code/code_evaluation.py","file_url":"https://github.com/cvs-health/uqlm/blob/HEAD/uqlm/code/code_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"60cdbbe10c98b7ab"}},{"code_sha256_prefix":"07a5d363bf4db8b3","entry":"evaluate_row_unified","repo":"cvs-health/uqlm","repo_kind":"official","path":"uqlm/code/code_evaluation.py","file_url":"https://github.com/cvs-health/uqlm/blob/HEAD/uqlm/code/code_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"07a5d363bf4db8b3"}},{"code_sha256_prefix":"68fb9511f08d5adb","entry":"make_function","repo":"cvs-health/uqlm","repo_kind":"official","path":"uqlm/code/lcb_grader.py","file_url":"https://github.com/cvs-health/uqlm/blob/HEAD/uqlm/code/lcb_grader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"68fb9511f08d5adb"}},{"code_sha256_prefix":"fc0bbef7e3b31704","entry":"sanitize_llm_output","repo":"cvs-health/uqlm","repo_kind":"official","path":"uqlm/code/code_evaluation.py","file_url":"https://github.com/cvs-health/uqlm/blob/HEAD/uqlm/code/code_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc0bbef7e3b31704"}},{"code_sha256_prefix":"993984482b377429","entry":"truncatefn","repo":"cvs-health/uqlm","repo_kind":"official","path":"uqlm/code/lcb_grader.py","file_url":"https://github.com/cvs-health/uqlm/blob/HEAD/uqlm/code/lcb_grader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"993984482b377429"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}