{"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/can-llms-express-their-uncertainty-an","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","arxiv_id":"2306.13063","date":"2023-06-22","proceeding":null,"authors":["Miao Xiong","Zhiyuan Hu","Xinyang Lu","Yifei Li","Jie Fu","Junxian He","Bryan Hooi"],"abstract":"Empowering large language models to accurately express confidence in their answers is essential for trustworthy decision-making. Previous confidence elicitation methods, which primarily rely on white-box access to internal model information or model fine-tuning, have become less suitable for LLMs, especially closed-source commercial APIs. This leads to a growing need to explore the untapped area of black-box approaches for LLM uncertainty estimation. To better break down the problem, we define a systematic framework with three components: prompting strategies for eliciting verbalized confidence, sampling methods for generating multiple responses, and aggregation techniques for computing consistency. We then benchmark these methods on two key tasks-confidence calibration and failure prediction-across five types of datasets (e.g., commonsense and arithmetic reasoning) and five widely-used LLMs including GPT-4 and LLaMA 2 Chat. Our analysis uncovers several key insights: 1) LLMs, when verbalizing their confidence, tend to be overconfident, potentially imitating human patterns of expressing confidence. 2) As model capability scales up, both calibration and failure prediction performance improve. 3) Employing our proposed strategies, such as human-inspired prompts, consistency among multiple responses, and better aggregation strategies can help mitigate this overconfidence from various perspectives. 4) Comparisons with white-box methods indicate that while white-box methods perform better, the gap is narrow, e.g., 0.522 to 0.605 in AUROC. Despite these advancements, none of these techniques consistently outperform others, and all investigated methods struggle in challenging tasks, such as those requiring professional knowledge, indicating significant scope for improvement. We believe this study can serve as a strong baseline and provide insights for eliciting confidence in black-box LLMs.","url_abs":"https://arxiv.org/abs/2306.13063v2","url_pdf":"https://arxiv.org/pdf/2306.13063v2.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":"can-llms-express-their-uncertainty-an","repo_url":"https://github.com/miaoxiong2320/llm-uncertainty","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"llama","method_name":"LLaMA"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.13063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.13063"}},"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":"deterministic:regex_extraction","url":"https://github.com/MiaoXiong2320/llm-uncertainty","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/miaoxiong2320/llm-uncertainty","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"46a375b86ef3f830","entry":"generate_misleading_hint","repo":"MiaoXiong2320/llm-uncertainty","repo_kind":"official","path":"query_multistep.py","file_url":"https://github.com/MiaoXiong2320/llm-uncertainty/blob/HEAD/query_multistep.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":"46a375b86ef3f830"}},{"code_sha256_prefix":"1e2b99754add3d96","entry":"generate_misleading_hint","repo":"miaoxiong2320/llm-uncertainty","repo_kind":"official","path":"query_vanilla_or_cot.py","file_url":"https://github.com/miaoxiong2320/llm-uncertainty/blob/HEAD/query_vanilla_or_cot.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":"1e2b99754add3d96"}},{"code_sha256_prefix":"6ad02b864df95421","entry":"generate_prompt","repo":"MiaoXiong2320/llm-uncertainty","repo_kind":"official","path":"query_multistep.py","file_url":"https://github.com/MiaoXiong2320/llm-uncertainty/blob/HEAD/query_multistep.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":"6ad02b864df95421"}},{"code_sha256_prefix":"1ad70628fb229a07","entry":"search_vis_answers","repo":"miaoxiong2320/llm-uncertainty","repo_kind":"official","path":"vis_aggregated_conf.py","file_url":"https://github.com/miaoxiong2320/llm-uncertainty/blob/HEAD/vis_aggregated_conf.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":"1ad70628fb229a07"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}