{"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/confidence-calibration-and-rationalization","title":"Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation","arxiv_id":"2404.09127","date":"2024-04-14","proceeding":null,"authors":["Ruixin Yang","Dheeraj Rajagopal","Shirley Anugrah Hayati","Bin Hu","Dongyeop Kang"],"abstract":"Uncertainty estimation is a significant issue for current large language models (LLMs) that are generally poorly calibrated and over-confident, especially with reinforcement learning from human feedback (RLHF). Unlike humans, whose decisions and confidences not only stem from intrinsic beliefs but can also be adjusted through daily observations, existing calibration methods for LLMs focus on estimating or eliciting individual confidence without taking full advantage of the \"Collective Wisdom\": the interaction among multiple LLMs that can collectively improve both accuracy and calibration. In this work, we propose Collaborative Calibration, a post-hoc training-free calibration strategy that leverages the collaborative and expressive capabilities of multiple tool-augmented LLM agents in a simulated group deliberation process. We demonstrate the effectiveness of Collaborative Calibration on generative QA tasks across various domains, showing its potential in harnessing the rationalization of collectively calibrated confidence assessments and improving the reliability of model predictions.","url_abs":"https://arxiv.org/abs/2404.09127v3","url_pdf":"https://arxiv.org/pdf/2404.09127v3.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":"confidence-calibration-and-rationalization","repo_url":"https://github.com/minnesotanlp/collaborative-calibration","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.09127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09127"}},"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/minnesotanlp/collaborative-calibration","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"29c9baba710b8f9d","entry":"brier_score","repo":"minnesotanlp/collaborative-calibration","repo_kind":"official","path":"collaborative-calibration/analysis_utils.py","file_url":"https://github.com/minnesotanlp/collaborative-calibration/blob/HEAD/collaborative-calibration/analysis_utils.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":"29c9baba710b8f9d"}},{"code_sha256_prefix":"90d7825b0ed1e03b","entry":"extract_ans","repo":"minnesotanlp/collaborative-calibration","repo_kind":"official","path":"collaborative-calibration/simulation_utils.py","file_url":"https://github.com/minnesotanlp/collaborative-calibration/blob/HEAD/collaborative-calibration/simulation_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"90d7825b0ed1e03b"}},{"code_sha256_prefix":"8f18345b4aa8c821","entry":"extract_conf","repo":"minnesotanlp/collaborative-calibration","repo_kind":"official","path":"collaborative-calibration/simulation_utils.py","file_url":"https://github.com/minnesotanlp/collaborative-calibration/blob/HEAD/collaborative-calibration/simulation_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f18345b4aa8c821"}},{"code_sha256_prefix":"5051f41b33a1ebb5","entry":"extract_conf_metrics","repo":"minnesotanlp/collaborative-calibration","repo_kind":"official","path":"collaborative-calibration/simulation_utils.py","file_url":"https://github.com/minnesotanlp/collaborative-calibration/blob/HEAD/collaborative-calibration/simulation_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5051f41b33a1ebb5"}},{"code_sha256_prefix":"22cc73f718dcedbb","entry":"interval_ece","repo":"minnesotanlp/collaborative-calibration","repo_kind":"official","path":"collaborative-calibration/analysis_utils.py","file_url":"https://github.com/minnesotanlp/collaborative-calibration/blob/HEAD/collaborative-calibration/analysis_utils.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":"22cc73f718dcedbb"}},{"code_sha256_prefix":"726eb5011c800373","entry":"load_entailment_classifier","repo":"minnesotanlp/collaborative-calibration","repo_kind":"official","path":"collaborative-calibration/load_pretrained.py","file_url":"https://github.com/minnesotanlp/collaborative-calibration/blob/HEAD/collaborative-calibration/load_pretrained.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":"726eb5011c800373"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}