{"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/when-an-llm-is-apprehensive-about-its-answers","title":"When an LLM is apprehensive about its answers -- and when its uncertainty is justified","arxiv_id":"2503.01688","date":"2025-03-03","proceeding":null,"authors":["Petr Sychev","Andrey Goncharov","Daniil Vyazhev","Edvard Khalafyan","Alexey Zaytsev"],"abstract":"Uncertainty estimation is crucial for evaluating Large Language Models (LLMs), particularly in high-stakes domains where incorrect answers result in significant consequences. Numerous approaches consider this problem, while focusing on a specific type of uncertainty, ignoring others. We investigate what estimates, specifically token-wise entropy and model-as-judge (MASJ), would work for multiple-choice question-answering tasks for different question topics. Our experiments consider three LLMs: Phi-4, Mistral, and Qwen of different sizes from 1.5B to 72B and $14$ topics. While MASJ performs similarly to a random error predictor, the response entropy predicts model error in knowledge-dependent domains and serves as an effective indicator of question difficulty: for biology ROC AUC is $0.73$. This correlation vanishes for the reasoning-dependent domain: for math questions ROC-AUC is $0.55$. More principally, we found out that the entropy measure required a reasoning amount. Thus, data-uncertainty related entropy should be integrated within uncertainty estimates frameworks, while MASJ requires refinement. Moreover, existing MMLU-Pro samples are biased, and should balance required amount of reasoning for different subdomains to provide a more fair assessment of LLMs performance.","url_abs":"https://arxiv.org/abs/2503.01688v1","url_pdf":"https://arxiv.org/pdf/2503.01688v1.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":"when-an-llm-is-apprehensive-about-its-answers","repo_url":"https://github.com/LabARSS/question-complextiy-estimation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"mmlu","task_name":"MMLU"},{"task_slug":"math","task_name":"Math"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.01688","atlas_url":"https://app.syntology.ai/?focus=2503.01688","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}