Do Large Language Models Know What They Don’t Know?
Open accessAbstract
Large language models (LLMs) have a wealth of knowledge that allows them to excel in various Natural Language Processing (NLP) tasks.Current research focuses on enhancing their performance within their existing knowledge.Despite their vast knowledge, LLMs are still limited by the amount of information they can accommodate and comprehend.Therefore, the ability to understand their own limitations on the unknows, referred to as self-knowledge, is of paramount importance.This study aims to evaluate LLMs' self-knowledge by assessing their ability to identify unanswerable or unknowable questions.We introduce an automated methodology to detect uncertainty in the responses of these models, providing a novel measure of their self-knowledge.We further introduce a unique dataset, SelfAware, consisting of unanswerable questions from five diverse categories and their answerable counterparts.Our extensive analysis, involving 20 LLMs including GPT-3, InstructGPT, and LLaMA, discovering an intrinsic capacity for self-knowledge within these models.Moreover, we demonstrate that in-context learning and instruction tuning can further enhance this self-knowledge.Despite this promising insight, our findings also highlight a considerable gap between the capabilities of these models and human proficiency in recognizing the limits of their knowledge. "True wisdom is knowing what you don't know." -Confucius
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
There is a discrepancy between surface realization and inherent knowledge of the model in NLG tasks.
“current research works [21, 113, 174, 212, 298] highlight a discrepancy between surface realization and inherent knowledge of the model in NLG tasks.”
From Survey of Hallucination in Natural Language Generation (2023) · cites this paper as [298]
The Introduction distinguishes a model’s stored knowledge from its ability to understand and use that knowledge, and the Evaluation Method assesses self-knowledge through generated responses. But the paper does not establish the claimed discrepancy between surface realization and inherent knowledge across NLG tasks; its study concerns responses to answerable and unanswerable questions. The indexed passages provide section labels but no page numbers. (LLM, conf=0.72)
Experimental — accuracy not yet measuredWhen an agent encounters unknowns, arbitrary decisions can be perilous.
“As highlighted in Yin et al. (2023) and Cheng et al. (2024), when agent i encounters unknowns, arbitrary decisions can be perilous.”
From From Imitation to Introspection: Probing Self-Consciousness in Language Models (2025) · cites this paper as Yin et al., 2023
The Introduction (page unavailable) says LLMs should recognize their limitations and convey uncertainty when facing unknowable questions to ensure responsible use. Section 2.1 likewise says they should express uncertainty rather than give conclusive responses. The paper does not establish that arbitrary decisions by agents are perilous; it addresses LLM responses to questions. (LLM, conf=0.81)
Experimental — accuracy not yet measuredKnown-Unknown and SelfAware evaluated LLMs' awareness of uncertainty for questions without definitive answer.
“Known-Unknown [5, 7] and SeflAware [299] evaluated LLMs' awareness of uncertainty for question without definitive answer”
From Survey of Hallucination in Natural Language Generation (2023) · cites this paper as [299]
SelfAware is a novel benchmark consisting of five categories of unanswerable questions.
“SelfAware (Yin et al., 2023), a novel benchmark consisting of five categories of unanswerable questions.”
From From Imitation to Introspection: Probing Self-Consciousness in Language Models (2025) · cites this paper as Yin et al., 2023
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208 · see citing works
Self-citationTriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Joshi, M., Choi, E., Weld, D., & Zettlemoyer, L. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1147 · Cited by 1,690 · see citing works
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. (2023) · arXiv · doi:10.48550/arxiv.2305.10601 · Cited by 1,158 · see citing works
Reflexion: Language Agents with Verbal Reinforcement Learning
Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087 · see citing works
NewsQA: A Machine Comprehension Dataset
Trischler, A., Wang, T., Yuan, X., Harris, J., Sordoni, A., Bachman, P., & Suleman, K. (2017) · Proceedings of the 2nd Workshop on Representation Learning for NLP · doi:10.18653/v1/w17-2623 · Cited by 706 · see citing works
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., Santoro, A., Gupta, A., Garriga-Alonso, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.04615 · Cited by 569 · see citing works
Solving Quantitative Reasoning Problems with Language Models
Lewkowycz, A., Andreassen, A., Dohan, D., Dyer, E., Michalewski, H., Ramasesh, V., Slone, A., Anil, C., Schlag, I., Gutman-Solo, T., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.14858 · Cited by 358 · see citing works
Language Models (Mostly) Know What They Know
Kadavath, S., Conerly, T., Askell, A., Henighan, T., Drain, D., Perez, E., Schiefer, N., Hatfield-Dodds, Z., DasSarma, N., Tran-Johnson, E., et al. (2022) · arXiv · doi:10.48550/arxiv.2207.05221 · Cited by 187 · see citing works
Flagged first, then by citations
Research works printed but not linked: 12
- Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Ad- vances in Neural Information Processing Systems 33: Annual Conference on Neural Information Process- ing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
- Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W Cohen. 2022. Program of thoughts prompting: Disentangling computation from reason- ing for numerical reasoning tasks. ArXiv preprint, abs/2211.12588. · arXiv
- Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. 2022. Complexity-based prompt- ing for multi-step reasoning. ArXiv preprint, abs/2210.00720. · arXiv
- Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. SimCSE: Simple contrastive learning of sentence em- beddings. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Process- ing, pages 6894-6910, Online and Punta Cana, Do- minican Republic. Association for Computational Linguistics. · DOI · Paper page
- Xiaonan Li and Xipeng Qiu. 2023. Mot: Pre- thinking and recalling enable chatgpt to self- improve with memory-of-thoughts. ArXiv preprint, abs/2305.05181. · arXiv
- Pranav Rajpurkar, Robin Jia, and Percy Liang. 2018. Know what you don't know: Unanswerable ques- tions for SQuAD. In Proceedings of the 56th Annual Meeting of the Association for Computational Lin- guistics (Volume 2: Short Papers), pages 784-789, Melbourne, Australia. Association for Computational Linguistics. · DOI · Paper page
- Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natu- ral Language Processing, pages 2383-2392, Austin, Texas. Association for Computational Linguistics. · DOI · Paper page
- Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. ArXiv preprint, abs/2302.13971. · arXiv
- Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, and Denny Zhou. 2022. Self-consistency im- proves chain of thought reasoning in language mod- els. ArXiv preprint, abs/2203.11171. · arXiv
- Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed H. Chi, Quoc V Le, and Denny Zhou. 2022. Chain of thought prompt- ing elicits reasoning in large language models. In Advances in Neural Information Processing Systems.
- Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christo- pher D. Manning. 2018. HotpotQA: A dataset for diverse, explainable multi-hop question answering. In Proceedings of the 2018 Conference on Empiri- cal Methods in Natural Language Processing, pages 2369-2380, Brussels, Belgium. Association for Com- putational Linguistics. · DOI · Paper page
- Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Olivier Bousquet, Quoc Le, and Ed Chi. 2022. Least-to-most prompting enables complex reason- ing in large language models. ArXiv preprint, abs/2205.10625. · arXiv
Cited by
Sorted by citations
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · see citing works
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3703155 · Cited by 2,142 · see citing works
Towards Accurate Differential Diagnosis with Large Language Models
McDuff, D., Schaekermann, M., Tu, T., Palepu, A., Wang, A., Garrison, J., Singhal, K., Sharma, Y., Azizi, S., Kulkarni, K., et al. (2023) · arXiv · doi:10.48550/arxiv.2312.00164 · Cited by 311 · see citing works
Towards accurate differential diagnosis with large language models
McDuff, D., Schaekermann, M., Tu, T., Palepu, A., Wang, A., Garrison, J., Singhal, K., Sharma, Y., Azizi, S., Kulkarni, K., et al. (2025) · Nature · doi:10.1038/s41586-025-08869-4 · Cited by 311 · see citing works
Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
Dahl, M., Magesh, V., Suzgun, M., & Ho, D. E. (2024) · Journal of Legal Analysis · doi:10.1093/jla/laae003 · Cited by 288 · see citing works
What large language models know and what people think they know
Steyvers, M., Tejeda, H., Kumar, A., Belem, C., Karny, S., Hu, X., Mayer, L. W., & Smyth, P. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-024-00976-7 · Cited by 209 · see citing works
The clinicians’ guide to large language models: a general perspective with a focus on hallucinations
Roustan, D., & Bastardot, F. (2025) · Interactive Journal of Medical Research · doi:10.2196/59823 · Cited by 191 · see citing works
A Survey of Confidence Estimation and Calibration in Large Language Models . -
Geng, J., Cai, F., Wang, Y., Koeppl, H., Nakov, P., & Gurevych, I. (2024) · Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · doi:10.18653/v1/2024.naacl-long.366 · Cited by 88 · see citing works
HalluLens: LLM Hallucination Benchmark
Bang, Y., Ji, Z., Schelten, A., Hartshorn, A., Fowler, T., Zhang, C., Cancedda, N., & Fung, P. (2025) · Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2025.acl-long.1176 · Cited by 41 · see citing works
Large language models in peer review: challenges and opportunities
Sun, Z. (2025) · Scientometrics · doi:10.1007/s11192-025-05440-w · Cited by 15 · see citing works
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
Chen, J., Yoon, J., Ebrahimi, S., Arik, S., Pfister, T., & Jha, S. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.345 · Cited by 13 · see citing works
The Hallucination Tax of Reinforcement Finetuning
Song, L., Shi, T., & Zhao, J. (2025) · Findings of the Association for Computational Linguistics: EMNLP 2025 · doi:10.18653/v1/2025.findings-emnlp.112 · Cited by 10 · see citing works
Calibrating the Confidence of Large Language Models by Eliciting Fidelity
Zhang, M., Huang, M., Shi, R., Guo, L., Peng, C., Yan, P., Zhou, Y., & Qiu, X. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.173 · Cited by 11 · see citing works
Self-citationCharacterizing LLM Abstention Behavior in Science QA with Context Perturbations
Wen, B., Howe, B., & Wang, L. L. (2024) · arXiv · doi:10.48550/arxiv.2404.12452 · Cited by 5 · see citing works
From Imitation to Introspection: Probing Self-Consciousness in Language Models
Chen, S., Yu, S., Zhao, S., & Lu, C. (2025) · Findings of the Association for Computational Linguistics: ACL 2025 · doi:10.18653/v1/2025.findings-acl.392 · Cited by 4 · see citing works
Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers
Wang, Y., Reddy, R. G., Mujahid, Z. M., Arora, A., Rubashevskii, A., Geng, J., Afzal, O. M., Pan, L., Borenstein, N., Pillai, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.09000 · Cited by 3 · see citing works
- Authors
- Yin, Z., Sun, Q., Guo, Q., Wu, J., Qiu, X., & Huang, X.
- Affiliations
- National University of Singapore (SG)
- Corresponding author
- Huang, Xuanjing
- Venue
- Findings of the Association for Computational Linguistics: ACL 2023
- Published
- 2023
- Pages
- 8653-8665
- OpenAlex
- W4385571050
- Cited by
- 75
- References
- 8
- Citations by year
- 2026: 20 · 2025: 28 · 2024: 18 · 2023: 9
- FWCI
- 13.29
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: ACL (Findings of ACL) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62236004, 62022027)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- large language models, self-knowledge, uncertainty detection, unanswerable questions, in-context learning, instruction tuning, model limitations, GPT-3, llamas
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
