{"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/fact-and-reflection-far-improves-confidence","title":"Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models","arxiv_id":"2402.17124","date":"2024-02-27","proceeding":null,"authors":["Xinran Zhao","Hongming Zhang","Xiaoman Pan","Wenlin Yao","Dong Yu","Tongshuang Wu","Jianshu Chen"],"abstract":"For a LLM to be trustworthy, its confidence level should be well-calibrated with its actual performance. While it is now common sense that LLM performances are greatly impacted by prompts, the confidence calibration in prompting LLMs has yet to be thoroughly explored. In this paper, we explore how different prompting strategies influence LLM confidence calibration and how it could be improved. We conduct extensive experiments on six prompting methods in the question-answering context and we observe that, while these methods help improve the expected LLM calibration, they also trigger LLMs to be over-confident when responding to some instances. Inspired by human cognition, we propose Fact-and-Reflection (FaR) prompting, which improves the LLM calibration in two steps. First, FaR elicits the known \"facts\" that are relevant to the input prompt from the LLM. And then it asks the model to \"reflect\" over them to generate the final answer. Experiments show that FaR prompting achieves significantly better calibration; it lowers the Expected Calibration Error by 23.5% on our multi-purpose QA tasks. Notably, FaR prompting even elicits the capability of verbally expressing concerns in less confident scenarios, which helps trigger retrieval augmentation for solving these harder instances.","url_abs":"https://arxiv.org/abs/2402.17124v2","url_pdf":"https://arxiv.org/pdf/2402.17124v2.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":"fact-and-reflection-far-improves-confidence","repo_url":"https://github.com/colinzhaoust/fact-and-reflection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.17124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17124"}},"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/colinzhaoust/fact-and-reflection","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"7065bc6a2b841da5","entry":"compute_exact","repo":"colinzhaoust/fact-and-reflection","repo_kind":"official","path":"public_code.py","file_url":"https://github.com/colinzhaoust/fact-and-reflection/blob/HEAD/public_code.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7065bc6a2b841da5"}},{"code_sha256_prefix":"924acab8dbf97406","entry":"load_strategyqa","repo":"colinzhaoust/fact-and-reflection","repo_kind":"official","path":"public_code.py","file_url":"https://github.com/colinzhaoust/fact-and-reflection/blob/HEAD/public_code.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"924acab8dbf97406"}},{"code_sha256_prefix":"55e919890251f878","entry":"normalize_answer","repo":"colinzhaoust/fact-and-reflection","repo_kind":"official","path":"public_code.py","file_url":"https://github.com/colinzhaoust/fact-and-reflection/blob/HEAD/public_code.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"55e919890251f878"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}