Elamur Research⌕
☰
home / papers / 2025 / MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs

MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs

Paper · 2025 · Gabrielle Kaili-May Liu, Gal Yona, Avi Caciularu et al.

Summary

LLMs often state false claims in confident language, which leads users to over-trust them. This paper studies "faithful calibration": whether the decisiveness of a model's wording matches its intrinsic uncertainty. This differs from standard factual calibration, which ties confidence to accuracy. The authors benchmark 19 models on 10 datasets spanning 6 content domains, using 5 uncertainty elicitation prompts. Each response is split into assertions. An LLM judge rates each assertion's decisiveness, and intrinsic confidence is estimated from consistency with resampled answers. Most models are poorly calibrated in this sense. Generic hedging instructions help only marginally, few-shot exemplars are not enough, and factuality-oriented calibration methods can even reduce faithfulness. The authors then introduce MetaFaith, a training-free, black-box method in which a master prompt guides a generator LLM to write system-level calibration prompts grounded in metacognitive strategies. A single MetaFaith prompt improves faithfulness by up to 61% across models and domains, offering a cheap route to more honest uncertainty expression.

Key points

  • The metric is faithful response uncertainty (following Yona et al., 2024): one minus the mean absolute gap between each assertion's decisiveness and the model's intrinsic confidence. Intrinsic confidence uses a Manakul et al. (2023)-style consistency check against K sampled responses.
  • The study also tests 12 advanced prompt strategies. MetaFaith with one shared prompt beats per-dataset prompt baselines, and an ablation shows that removing the explicit metacognitive part eliminates the systematic gains.
  • In human evaluation, MetaFaith outputs win 83% of comparisons against a simple uncertainty-elicitation baseline, with high inter-annotator agreement.
  • Simple hedging prompts raise the average rate of declining to answer from about 1% to about 7%, lowering accuracy. MetaFaith keeps this rate near 2% by qualifying answers instead of refusing.
  • Experiments are English-only, and the authors flag cross-lingual and cultural differences in uncertainty markers as open problems. Code is available at github.com/yale-nlp/MetaFaith.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🏢GoogleMountain View · United States430 works · 424,363 citations🎓University of TorontoToronto · Canada96 works · 142,007 citations🎓Yale UniversityNew Haven · United States95 works · 12,765 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Gabrielle Kaili-May Liu, Gal Yona, Avi Caciularu, Idan Szpektor, Tim G. J. Rudner and Arman Cohan. 2025. MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.emnlp-main.1505

@inproceedings{liu2025metafaith,
  title = {{MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs}},
  author = {Gabrielle Kaili-May Liu, Gal Yona, Avi Caciularu, Idan Szpektor, Tim G. J. Rudner and Arman Cohan},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  doi = {10.18653/v1/2025.emnlp-main.1505},
  url = {https://doi.org/10.18653/v1/2025.emnlp-main.1505}
}

References

126 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Anthropic. The claude 3 model family: Opus, sonnet, haiku. find
  2. Amos Azaria and Tom Mitchell. 2023. The internal state of an LLM knows when it‘s lying. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 967–976, Singapore. Association for Computational Linguistics.
  3. Joris Baan, Nico Daheim, Evgenia Ilia, Dennis Ulmer, Haau-Sing Li, R. Fernández, Barbara Plank, Rico Sennrich, Chrysoula Zerva, and Wilker Aziz. 2023. Uncertainty in natural language generation: From theory to applications. ArXiv, abs/2307.15703. — [arXiv:2307.15703](https://arxiv.org/abs/2307.15703) find
  4. Neil Band, Xuechen Li, Tengyu Ma, and Tatsunori Hashimoto. 2024. Linguistic calibration of long-form generations. Preprint, arXiv:2404.00474. — [arXiv:2404.00474](https://arxiv.org/abs/2404.00474) find
  5. Evan Becker and Stefano Soatto. 2024. Cycles of thought: Measuring llm confidence through stable explanations. Preprint, arXiv:2406.03441. — [arXiv:2406.03441](https://arxiv.org/abs/2406.03441) find
  6. Glenn W Brier. 1950. Verification of forecasts expressed in terms of probability. Monthly weather review, 78(1):1–3. find
  7. David V Budescu and Thomas S Wallsten. 1985. Consistency in interpretation of probabilistic phrases. Organizational Behavior and Human Decision Processes, 36(3):391–405. find
  8. Collin Burns, Haotian Ye, Dan Klein, and Jacob Steinhardt. 2024. Discovering latent knowledge in language models without supervision. Preprint, arXiv:2212.03827. find
  9. Carrie J. Cai, Samantha Winter, David Steiner, Lauren Wilcox, and Michael Terry. 2019. "hello ai": Uncovering the onboarding needs of medical practitioners for human-ai collaborative decision-making. Proc. ACM Hum.-Comput. Interact., 3(CSCW). find
  10. Arslan Chaudhry, Sridhar Thiagarajan, and Dilan Gorur. 2024. Finetuning language models to emit linguistic expressions of uncertainty. Preprint, arXiv:2409.12180. — [arXiv:2409.12180](https://arxiv.org/abs/2409.12180) find
  11. Banghao Chen, Zhaofeng Zhang, Nicolas Langrené, and Shengxin Zhu. 2024a. Unleashing the potential of prompt engineering in large language models: a comprehensive review. Preprint, arXiv:2310.14735.
  12. Haozhe Chen, Carl Vondrick, and Chengzhi Mao. 2024b. Selfie: Self-interpretation of large language model embeddings. Preprint, arXiv:2403.10949. — [arXiv:2403.10949](https://arxiv.org/abs/2403.10949) find
  13. Jiuhai Chen and Jonas Mueller. 2024. Quantifying uncertainty in answers from any language model and enhancing their trustworthiness. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5186–5200, Bangkok, Thailand. Association for…
  14. Yanda Chen, Joe Benton, Ansh Radhakrishnan, Jonathan Uesato, Carson Denison, John Schulman, Arushi Somani, Peter Hase, Misha Wagner, Fabien Roger, and 1 others. 2025. Reasoning models don’t always say what they think. arXiv preprint arXiv:2505.05410. find
  15. Yangyi Chen, Lifan Yuan, Ganqu Cui, Zhiyuan Liu, and Heng Ji. 2023. A close look into the calibration of pre-trained language models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1343–1367, Toronto, Canada. Association for… find
  16. Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. 2018. Think you have solved question answering? try arc, the ai2 reasoning challenge. arXiv:1803.05457v1.
  17. Matthew Dahl, Varun Magesh, Mirac Suzgun, and Daniel E. Ho. 2024. Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models.
  18. Shrey Desai and Greg Durrett. 2020. Calibration of pre-trained transformers. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 295–302, Online. Association for Computational Linguistics. find
  19. Michael Curtis Mozer, and Sanjeev Arora. 2024. Metacognitive capabilities of LLMs: An exploration in mathematical problem solving. In AI for Math Workshop @ ICML 2024. find
  20. Jinhao Duan, Hao Cheng, Shiqi Wang, Alex Zavalny, Chenan Wang, Renjing Xu, Bhavya Kailkhura, and Kaidi Xu. 2024. Shifting attention to relevance: Towards the predictive uncertainty quantification of free-form large language models. In Proceedings of the 62nd Annual Meeting of the Association for Com… find
  21. Ekaterina Fadeeva, Roman Vashurin, Akim Tsvigun, Artem Vazhentsev, Sergey Petrakov, Kirill Fedyanin, Daniil Vasilev, Elizaveta Goncharova, Alexander Panchenko, Maxim Panov, Timothy Baldwin, and Artem Shelmanov. 2023. LM-polygraph: Uncertainty estimation for language models. In Proceedings of the 202… find
  22. Wade Fagen-Ulmschneider. 2023. Perception of probability words. find
  23. Stephen Fleming and Hakwan Lau. 2014. How to measure metacognition. Frontiers in Human Neuroscience, 8:443. find
  24. Zorik Gekhman, Gal Yona, Roee Aharoni, Matan Eyal, Amir Feder, Roi Reichart, and Jonathan Herzig. 2024. Does fine-tuning LLMs on new knowledge encourage hallucinations? In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7765–7784, Miami, Florida, USA. As… find
  25. Jiahui Geng, Fengyu Cai, Yuxia Wang, Heinz Koeppl, Preslav Nakov, and Iryna Gurevych. 2024. A survey of confidence estimation and calibration in large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language… find
  26. Bijean Ghafouri, Shahrad Mohammadzadeh, James Zhou, Pratheeksha Nair, Jacob-Junqi Tian, Mayank Goel, Reihaneh Rabbany, Jean-François Godbout, and Kellin Pelrine. 2024. Epistemic integrity in large language models. In Neurips Safe Generative AI Workshop 2024. find
  27. Mandeep Dhami and David Mandel. 2022. Communicating uncertainty using words and numbers. Trends in Cognitive Sciences, 26. find
  28. Asma Ghandeharioun, Avi Caciularu, Adam Pearce, Lucas Dixon, and Mor Geva. 2024. Patchscopes: A unifying framework for inspecting hidden representations of language models. Preprint, arXiv:2401.06102. find
  29. Aniket Rajiv Didolkar, Anirudh Goyal, Nan Rosemary Ke, Siyuan Guo, Michal Valko, Timothy P Lillicrap, Danilo Jimenez Rezende, Yoshua Bengio, Google Gemini Team. 2025. Gemini 2.0: Flash, flash-lite and pro. https://developers.googleblog.com/en/gemini-2-family-expands/. ↗
  30. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — The Llama 3 Herd of Models
  31. Yashvir S. Grewal, Edwin V. Bonilla, and Thang D. Bui. 2024. Improving uncertainty quantification in large language models via semantic embeddings. Preprint, arXiv:2410.22685. — [arXiv:2410.22685](https://arxiv.org/abs/2410.22685) find
  32. Maxime Griot, Coralie Hemptinne, Jean Vanderdonckt, and Demet Yuksel. 2025. Large language models lack essential metacognition for reliable medical reasoning. Nature Communications, 16. find
  33. Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q. Weinberger. 2017. On calibration of modern neural networks. In Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 1321– 1330. PMLR. find
  34. Sree Harsha Tanneru, Chirag Agarwal, and Himabindu Lakkaraju. 2024. Quantifying uncertainty in natural language explanations of large language models. In Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, volume 238 of Proceedings of Machine Learning Research… find
  35. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021a. Measuring massive multitask language understanding. Preprint, arXiv:2009.03300.
  36. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021b. Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:2103.03874.
  37. Yihuai Hong, Dian Zhou, Meng Cao, Lei Yu, and Zhijing Jin. 2025. The reasoning-memorization interplay in language models is mediated by a single direction. Preprint, arXiv:2503.23084. find
  38. Bairu Hou, Yujian Liu, Kaizhi Qian, Jacob Andreas, Shiyu Chang, and Yang Zhang. 2024. Decomposing uncertainty for large language models through input clarification ensembling. Preprint, arXiv:2311.08718. — [arXiv:2311.08718](https://arxiv.org/abs/2311.08718) find
  39. Hsiu-Yuan Huang, Yutong Yang, Zhaoxi Zhang, Sanwoo Lee, and Yunfang Wu. 2024. A survey of uncertainty estimation in llms: Theory meets practice. Preprint, arXiv:2410.15326. — [arXiv:2410.15326](https://arxiv.org/abs/2410.15326) find
  40. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2025a. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Trans. Inf. Syst., 43(2).
  41. Yuheng Huang, Jiayang Song, Zhijie Wang, Shengming Zhao, Huaming Chen, Felix Juefei-Xu, and Lei Ma. 2025b. Look before you leap: An exploratory study of uncertainty analysis for large language models. IEEE Transactions on Software Engineering, 51(2):413–429. find
  42. Alon Jacovi and Yoav Goldberg. 2020. Towards faithfully interpretable NLP systems: How should we define and evaluate faithfulness? In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4198–4205, Online. Association for Computational Linguistics.
  43. Ziwei Ji, Lei Yu, Yeskendir Koishekenov, Yejin Bang, Anthony Hartshorn, Alan Schelten, Cheng Zhang, Pascale Fung, and Nicola Cancedda. 2025. Calibrating verbal uncertainty as a linear feature to reduce hallucinations. arXiv preprint arXiv:2503.14477.
  44. Mingjian Jiang, Yangjun Ruan, Sicong Huang, Saifei Liao, Silviu Pitis, Roger Baker Grosse, and Jimmy Ba. 2023. Calibrating language models via augmented prompt ensembles. find
  45. Zhengbao Jiang, Jun Araki, Haibo Ding, and Graham Neubig. 2021. How can we know when language models know? on the calibration of language models for question answering. Transactions of the Association for Computational Linguistics, 9:962–977. find
  46. Zhengping Jiang, Anqi Liu, and Benjamin Van Durme. 2025. Conformal linguistic calibration: Trading-off between factuality and specificity. Preprint, arXiv:2502.19110. — [arXiv:2502.19110](https://arxiv.org/abs/2502.19110) find
  47. Matt Gardner Johannes Welbl, Nelson F. Liu. 2017. Crowdsourcing multiple choice science questions.
  48. Douglas B. Johnson, Rachel S Goodman, J. Randall Patrinely, Cosby A Stone, Eli Zimmerman, Rebecca Rigel Donald, Sam S Chang, Sean T Berkowitz, Avni P Finn, Eiman Jahangir, Elizabeth A Scoville, Tyler Reese, Debra E. Friedman, Julie A. Bastarache, Yuri F van der Heijden, Jordan Wright, Nicholas Carte… find
  49. Mandar Joshi, Eunsol Choi, Daniel Weld, and Luke Zettlemoyer. 2017. triviaqa: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension. arXiv e-prints, arXiv:1705.03551.
  50. Saurav Kadavath, Tom Conerly, Amanda Askell, Tom Henighan, Dawn Drain, Ethan Perez, Nicholas Schiefer, Zac Hatfield-Dodds, Nova DasSarma, Eli Tran-Johnson, Scott Johnston, Sheer El-Showk, Andy Jones, Nelson Elhage, Tristan Hume, Anna Chen, Yuntao Bai, Sam Bowman, Stanislav Fort, and 17 others. 2022.… find
  51. Amita Kamath, Robin Jia, and Percy Liang. 2020. Selective question answering under domain shift. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5684– 5696, Online. Association for Computational Linguistics. find
  52. Ramneet Kaur, Colin Samplawski, Adam D. Cobb, Anirban Roy, Brian Matejek, Manoj Acharya, Daniel Elenius, Alexander Michael Berenbeim, John A. Pavlik, Nathaniel D. Bastian, and Susmit Jha. 2024. Addressing uncertainty in LLMs to enhance reliability in generative AI. In Neurips Safe Generative AI Work… find
  53. Sunnie S. Y. Kim, Q. Vera Liao, Mihaela Vorvoreanu, Stephanie Ballard, and Jennifer Wortman Vaughan. 2024. "i’m not sure, but...": Examining the impact of large language models’ uncertainty expression on user reliance and trust. In Proceedings of the 2024 ACM Conference on Fairness, Accountability,… find
  54. Oliver Kramer. 2025. Conceptual metaphor theory as a prompting paradigm for large language models. Preprint, arXiv:2502.01901. — [arXiv:2502.01901](https://arxiv.org/abs/2502.01901) find
  55. Lorenz Kuhn, Yarin Gal, and Sebastian Farquhar. 2023. Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation. In The Eleventh International Conference on Learning Representations. find
  56. Abhishek Kumar, Robert Morabito, Sanzhar Umbet, Jad Kabbara, and Ali Emami. 2024. Confidence under the hood: An investigation into the confidence-probability alignment in large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long… find
  57. Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, and 4 other… — Tulu 3: Pushing Frontiers in Open Language Model Post-Training
  58. Shizuka Lauwereyns. 2002. Hedges in japanese conversation: The influence of age, sex, and formality. Language Variation and Change, 14(2):239–259. find
  59. Junyi Li, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, and Ji-Rong Wen. 2023. Halueval: A large-scale hallucination evaluation benchmark for large language models.
  60. Stephanie Lin, Jacob Hilton, and Owain Evans. 2022. Teaching models to express their uncertainty in words. Transactions on Machine Learning Research. find
  61. Qin Liu, Wenxuan Zhou, Nan Xu, James Y. Huang, Fei Wang, Sheng Zhang, Hoifung Poon, and Muhao Chen. 2025. Metascale: Test-time scaling with evolving meta-thoughts. Preprint, arXiv:2503.13447.
  62. Xin Liu, Muhammad Khalifa, and Lu Wang. 2024. Litcab: Lightweight language model calibration over short- and long-form responses. Preprint, arXiv:2310.19208. — [arXiv:2310.19208](https://arxiv.org/abs/2310.19208) find
  63. Qing Lyu, Marianna Apidianaki, and Chris Callison-Burch. 2024. Towards faithful model explanation in NLP: A survey. Computational Linguistics, 50(2):657–723.
  64. Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Hannaneh Hajishirzi, and Daniel Khashabi. 2022. When not to trust language models: Investigating effectiveness and limitations of parametric and non-parametric memories. arXiv preprint. find
  65. Potsawee Manakul, Adian Liusie, and Mark Gales. 2023. SelfCheckGPT: Zero-resource black-box hallucination detection for generative large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9004–9017, Singapore. Association for Computation… find
  66. Liam Mason, Sascha Wölk, Eran Eldar, and Robb Rutledge. 2024. Mood impacts confidence through biased learning of reward likelihood. bioRxiv. find
  67. Clara Meister, Gian Wiher, Tiago Pimentel, and Ryan Cotterell. 2022. On the probability–quality paradox in language generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 36–45, Dublin, Ireland. Association for Computati… find
  68. Sabrina J. Mielke, Arthur Szlam, Emily Dinan, and Y-Lan Boureau. 2022. Reducing conversational agents’ overconfidence through linguistic calibration. Transactions of the Association for Computational Linguistics, 10:857–872. find
  69. Pilar Mur-Dueñas. 2021. There may be differences: Analysing the use of hedges in english and spanish research articles. Lingua, 260:103131. find
  70. Mahdi Pakdaman Naeini, Gregory F. Cooper, and Milos Hauskrecht. 2015. Obtaining well calibrated probabilities using bayesian binning. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI’15, page 2901–2907. AAAI Press. find
  71. Thu Nguyen Thi Thuy. 2018. A corpus-based study on cross-cultural divergence in the use of hedges in academic research articles written by vietnamese and native english-speaking authors. Social Sciences, 7(4). find
  72. Shiyu Ni, Keping Bi, Lulu Yu, and Jiafeng Guo. 2024. Are large language models more honest in their probabilistic or verbalized confidence? Preprint, arXiv:2408.09773. — [arXiv:2408.09773](https://arxiv.org/abs/2408.09773) find
  73. Alexander Nikitin, Jannik Kossen, Yarin Gal, and Pekka Marttinen. 2024. Kernel language entropy: Fine-grained uncertainty quantification for llms from semantic similarities. Preprint, arXiv:2405.20003. — [arXiv:2405.20003](https://arxiv.org/abs/2405.20003) find
  74. Team OLMo, Pete Walsh, Luca Soldaini, Dirk Groeneveld, Kyle Lo, Shane Arora, Akshita Bhagia, Yuling Gu, Shengyi Huang, Matt Jordan, Nathan Lambert, Dustin Schwenk, Oyvind Tafjord, Taira Anderson, David Atkinson, Faeze Brahman, Christopher Clark, Pradeep Dasigi, Nouha Dziri, and 21 others. 2025. 2 ol… find
  75. OpenAI, :, Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander M adry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alex Kirillov, and 401 others. 2024. Gpt-4o system card.…
  76. Seo Yeon Park and Cornelia Caragea. 2022. On the calibration of pre-trained language models using mixup guided by area under the margin and saliency. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5364–5374, Dublin, Ireland.… find
  77. Jiabao Qiu, Zixuan Ke, and Bing Liu. 2025. Continual learning using only large language model prompting. In Proceedings of the 31st International Conference on Computational Linguistics, pages 6014– 6023, Abu Dhabi, UAE. Association for Computational Linguistics. find
  78. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. find
  79. Mauricio Rivera, Jean-François Godbout, Reihaneh Rabbany, and Kellin Pelrine. 2024. Combining confidence elicitation and sample-based methods for uncertainty quantification in misinformation mitigation. In Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024), pages 114–126, St… find
  80. Maohao Shen, Subhro Das, Kristjan Greenewald, Prasanna Sattigeri, Gregory Wornell, and Soumya Ghosh. 2024. Thermometer: Towards universal calibration for large language models. Preprint, arXiv:2403.08819. — [arXiv:2403.08819](https://arxiv.org/abs/2403.08819) find
  81. Vaishnavi Shrivastava, Percy Liang, and Ananya Kumar. 2023. Llamas know what gpts don’t show: Surrogate models for confidence estimation. Preprint, arXiv:2311.08877. find
  82. Chenglei Si, Zhe Gan, Zhengyuan Yang, Shuohang Wang, Jianfeng Wang, Jordan Lee Boyd-Graber, and Lijuan Wang. 2023. Prompting GPT-3 to be reliable. In The Eleventh International Conference on Learning Representations.
  83. Adi Simhi, Itay Itzhak, Fazl Barez, Gabriel Stanovsky, and Yonatan Belinkov. 2025. Trust me, i’m wrong: High-certainty hallucinations in llms. arXiv preprint arXiv:2502.12964. — [arXiv:2502.12964](https://arxiv.org/abs/2502.12964) find
  84. Aniket Kumar Singh, Bishal Lamichhane, Suman Devkota, Uttam Dhakal, and Chandra Dhakal. 2024. Do large language models show human-like biases? exploring confidence—competence gap in ai. Information, 15(2). find
  85. Elias Stengel-Eskin, Peter Hase, and Mohit Bansal. 2024. LACIE: Listener-aware finetuning for calibration in large language models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  86. Mark Steyvers, Heliodoro Tejeda, Aakriti Kumar, Catarina Belem, Sheer Karny, Xinyue Hu, Lukas W. Mayer, and Padhraic Smyth. 2025. What large language models know and what people think they know. Nature Machine Intelligence, 7(2):221–231. find
  87. YuHong Sun, Zhangyue Yin, Qipeng Guo, Jiawen Wu, Xipeng Qiu, and Hui Zhao. 2024. Benchmarking hallucination in large language models based on unanswerable math word problem. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LRE… find
  88. Zhisheng Tang, Ke Shen, and Mayank Kejriwal. 2024. An evaluation of estimative uncertainty in large language models. Preprint, arXiv:2405.15185. — [arXiv:2405.15185](https://arxiv.org/abs/2405.15185) find
  89. Katherine Tian, Eric Mitchell, Huaxiu Yao, Christopher D Manning, and Chelsea Finn. 2024. Fine-tuning language models for factuality. In The Twelfth International Conference on Learning Representations.
  90. Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, and Christopher Manning. 2023. Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback. In Proceedings of the 2023 Conferen… find
  91. SM Tonmoy, SM Zaman, Vinija Jain, Anku Rani, Vipula Rawte, Aman Chadha, and Amitava Das. 2024. A comprehensive survey of hallucination mitigation techniques in large language models. arXiv preprint arXiv:2401.01313, 6.
  92. Jason Toy, Josh MacAdam, and Phil Tabor. 2024. Metacognition is all you need? using introspection in generative agents to improve goal-directed behavior. Preprint, arXiv:2401.10910. — [arXiv:2401.10910](https://arxiv.org/abs/2401.10910) find
  93. Thomas S Wallsten, David V Budescu, Rami Zwick, and Steven M Kemp. 1993. Preferences and reasons for communicating probabilistic information in verbal or numerical terms. Bulletin of the Psychonomic Society, 31(2):135–138. find
  94. Alex Wang, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. SuperGLUE: A stickier benchmark for general-purpose language understanding systems. arXiv preprint 1905.00537.
  95. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 353–355,…
  96. Guoqing Wang, Wen Wu, Guangze Ye, Zhenxiao Cheng, Xi Chen, and Hong Zheng. 2025a. Decoupling metacognition from cognition: A framework for quantifying metacognitive ability in llms. Proceedings of the AAAI Conference on Artificial Intelligence, 39:25353–25361. find
  97. Peiqi Wang, Barbara D. Lam, Yingcheng Liu, Ameneh Asgari-Targhi, Rameswar Panda, William M Wells, Tina Kapur, and Polina Golland. 2025b. Calibrating expressions of certainty. In The Thirteenth International Conference on Learning Representations. find
  98. Yuqing Wang and Yun Zhao. 2024. Metacognitive prompting improves understanding in large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1914–1926, Mexico… find
  99. Jason Wei, Nguyen Karina, Hyung Won Chung, Yunxin Joy Jiao, Spencer Papay, Amelia Glaese, John Schulman, and William Fedus. 2024. Measuring short-form factuality in large language models. Preprint, arXiv:2411.04368.
  100. 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 prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems.
  101. Bingbing Wen, Chenjun Xu, Bin HAN, Robert Wolfe, Lucy Lu Wang, and Bill Howe. 2024. Mitigating overconfidence in large language models: A behavioral lens on confidence estimation and calibration. In NeurIPS 2024 Workshop on Behavioral Machine Learning. find
  102. Zhiqiu Xia, Jinxuan Xu, Yuqian Zhang, and Hang Liu. 2025. A survey of uncertainty estimation methods on large language models. Preprint, arXiv:2503.00172. find
  103. Yijun Xiao and William Yang Wang. 2021. On hallucination and predictive uncertainty in conditional language generation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2734–2744, Online. Association for Computational…
  104. Yuxin Xiao, Paul Pu Liang, Umang Bhatt, Willie Neiswanger, Ruslan Salakhutdinov, and Louis-Philippe Morency. 2022. Uncertainty quantification with pre-trained language models: A large-scale empirical analysis. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 7273–7284,… find
  105. Miao Xiong, Zhiyuan Hu, Xinyang Lu, YIFEI LI, Jie Fu, Junxian He, and Bryan Hooi. 2024. Can LLMs express their uncertainty? an empirical evaluation of confidence elicitation in LLMs. In The Twelfth International Conference on Learning Representations. find
  106. Yasin Abbasi Yadkori, Ilja Kuzborskij, András György, and Csaba Szepesvári. 2024. To believe or not to believe your llm. Preprint, arXiv:2406.02543. find
  107. Oktay Yagız and Cuneyt Demir. 2014. Hedging strategies in academic discourse: A comparative analysis of turkish writers and native writers of english. Procedia - Social and Behavioral Sciences, 158:260–268. 14th Language, Literature and Stylistics Symposium. find
  108. Daniel Yang, Yao-Hung Hubert Tsai, and Makoto Yamada. 2024a. On verbalized confidence scores for llms. Preprint, arXiv:2412.14737. — [arXiv:2412.14737](https://arxiv.org/abs/2412.14737) find
  109. Yuqing Yang, Ethan Chern, Xipeng Qiu, Graham Neubig, and Pengfei Liu. 2024b. Alignment for honesty. Preprint, arXiv:2312.07000. find
  110. Yuwei Yin, EunJeong Hwang, and Giuseppe Carenini. 2025. Swi: Speaking with intent in large language models. Preprint, arXiv:2503.21544. find
  111. Zhangyue Yin, Qiushi Sun, Qipeng Guo, Jiawen Wu, Xipeng Qiu, and Xuanjing Huang. 2023. Do large language models know what they don’t know? In Findings of the Association for Computational Linguistics: ACL 2023, pages 8653–8665, Toronto, Canada. Association for Computational Linguistics. find
  112. Gal Yona, Roee Aharoni, and Mor Geva. 2024. Can large language models faithfully express their intrinsic uncertainty in words? In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7752–7764, Miami, Florida, USA. Association for Computational Linguistics.
  113. Hanning Zhang, Shizhe Diao, Yong Lin, Yi R. Fung, Qing Lian, Xingyao Wang, Yangyi Chen, Heng Ji, and Tong Zhang. 2024a. R-tuning: Instructing large language models to say ‘i don’t know’. Preprint, arXiv:2311.09677. find
  114. Min Zhang, Jianfeng He, Taoran Ji, and Chang-Tien Lu. 2024b. Don‘t go to extremes: Revealing the excessive sensitivity and calibration limitations of LLMs in implicit hate speech detection. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pap… find
  115. Qiaoning Zhang, Matthew L Lee, and Scott Carter. 2022. You complete me: Human-ai teams and complementary expertise. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, CHI ’22, New York, NY, USA. Association for Computing Machinery. find
  116. Shengyu Zhang, Linfeng Dong, Xiaoya Li, Sen Zhang, Xiaofei Sun, Shuhe Wang, Jiwei Li, Runyi Hu, Tianwei Zhang, Fei Wu, and Guoyin Wang. 2024c. Instruction tuning for large language models: A survey. Preprint, arXiv:2308.10792.
  117. Yunfeng Zhang, Q. Vera Liao, and Rachel K. E. Bellamy. 2020. Effect of confidence and explanation on accuracy and trust calibration in ai-assisted decision making. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, FAT* ’20, page 295–305, New York, NY, USA. Associat… find
  118. Xinran Zhao, Hongming Zhang, Xiaoman Pan, Wenlin Yao, Dong Yu, Tongshuang Wu, and Jianshu Chen. 2024. Fact-and-reflection (FaR) improves confidence calibration of large language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 8702–8718, Bangkok, Thailand. Associ… find
  119. Wenliang Zheng, Sarkar Snigdha Sarathi Das, Yusen Zhang, and Rui Zhang. 2025. Greaterprompt: A unified, customizable, and high-performing open-source toolkit for prompt optimization. Preprint, arXiv:2504.03975. find
  120. Kaitlyn Zhou, Jena Hwang, Xiang Ren, and Maarten Sap. 2024a. Relying on the unreliable: The impact of language models’ reluctance to express uncertainty. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3623–3643, Bangkok, Thai… find
  121. Kaitlyn Zhou, Jena D. Hwang, Xiang Ren, Nouha Dziri, Dan Jurafsky, and Maarten Sap. 2025a. REL-A.I.: An interaction-centered approach to measuring human-LM reliance. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human L… find
  122. Kaitlyn Zhou, Dan Jurafsky, and Tatsunori Hashimoto. 2023. Navigating the grey area: How expressions of uncertainty and overconfidence affect language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5506–5524, Singapore. Association for Comput… find
  123. Yujia Zhou, Zheng Liu, Jiajie Jin, Jian-Yun Nie, and Zhicheng Dou. 2024b. Metacognitive retrieval-augmented large language models. Preprint, arXiv:2402.11626. — [arXiv:2402.11626](https://arxiv.org/abs/2402.11626) find
  124. Yuxiang Zhou, Hainiu Xu, Desmond C. Ong, Petr Slovak, and Yulan He. 2025b. Modeling subjectivity in cognitive appraisal with language models. Preprint, arXiv:2503.11381. find
  125. Ziang Zhou, Tianyuan Jin, Jieming Shi, and Qing Li. 2025c. Calibrating llm confidence with semantic steering: A multi-prompt aggregation framework. Preprint, arXiv:2503.02863. — [arXiv:2503.02863](https://arxiv.org/abs/2503.02863) find
  126. Alf C. Zimmer. 1983. Verbal vs. numerical processing of subjective probabilities. Advances in psychology, 16:159–182. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/liu-2025-metafaith-faithful-natural-language-uncertainty/