CoChat
Sign Up
Cited by 12Emotion and Mood RecognitionExplainable Artificial Intelligence (XAI)Sentiment Analysis and Opinion Mining

The DOI matches its Crossref record.

Mechanistic Interpretability of Emotion Inference in Large Language Models

Open access
Tak, Ala N., Banayeeanzade, Amin, Bolourani, Anahita, Kian, Mina, Jia, Robin, Gratch, Jonathan·2025·Findings of the Association for Computational Linguistics: ACL 2025
DOI 10.18653/v1/2025.findings-acl.679
Open this paper in CoChat — free accountOpen PDF

Abstract

Large language models (LLMs) show promising capabilities in predicting human emotions from text.However, the mechanisms through which these models process emotional stimuli remain largely unexplored.Our study addresses this gap by investigating how autoregressive LLMs infer emotions, showing that emotion representations are functionally localized to specific regions in the model.Our evaluation includes diverse model families and sizes, and is supported by robustness checks.We then show that the identified representations are psychologically plausible by drawing on cognitive appraisal theory-a well-established psychological framework positing that emotions emerge from evaluations (appraisals) of environmental stimuli.By causally intervening on construed appraisal concepts, we steer the generation and show that the outputs align with theoretical and intuitive expectations.This work highlights a novel way to causally intervene and control emotion inference, potentially benefiting safety and alignment in sensitive affective domains.Code at: GitHub repo.# Prompt Template 1 What are the inferred emotions in the following contexts?Context: My first child was born.Answer: joy Context: My dog died last week.Answer: sadness

Overview

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2025.findings-acl.679

Cites

Statistics

Verification

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • Some linear activation directions in LLM activations could stably encode some persona behaviors such as confidence, hallucination, and sycophancy.

    “Chen et al. (2025a); Wang et al. (2025c); Tak et al. (2025) find some linear activation directions in the LLM activations could stably encode some persona behaviors such as confidence, hallucination, and sycophancy”

    From Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy (2026) · cites this paper as Tak et al. (2025)

    Section 5, “Probing for Emotion Signals” (page unavailable), reports that linear classifiers detect emotion-related signals in LLM activations; Appendix C.5 reports that those probing results are robust across prompt templates. The paper does not establish stable activation directions for the cited persona behaviors—confidence, hallucination, or sycophancy. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

No references could be resolved yet.

Research works printed but not linked: 77

  1. Marah Abdin, Jyoti Aneja, Hany Awadalla, Ahmed Awadallah, Ammar Ahmad Awan, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, Harkirat Behl, et al. 2024. Phi-3 technical report: A highly ca- pable language model locally on your phone. arXiv preprint arXiv:2404.14219. · arXiv
  2. Yossi Adi, Einat Kermany, Yonatan Belinkov, Ofer Lavi, and Yoav Goldberg. 2017. Fine-grained analysis of sentence embeddings using auxiliary prediction tasks. In International Conference on Learning Representa- tions.
  3. Badr AlKhamissi, Greta Tuckute, Antoine Bosselut, and Martin Schrimpf. 2025. The LLM language network: A neuroscientific approach for identifying causally task-relevant units. In Proceedings of the 2025 Con- ference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 10887-10911, Albuquerque, New Mexico. As- sociation for Computational Linguistics.
  4. Khai Loong Aw, Syrielle Montariol, Badr AlKhamissi, Martin Schrimpf, and Antoine Bosselut. 2023. Instruction-tuning aligns llms to the human brain. arXiv preprint arXiv:2312.00575. · arXiv
  5. Lisa Feldman Barrett. 2017. The theory of constructed emotion: an active inference account of interoception and categorization. Social cognitive and affective neuroscience, 12(1):1-23.
  6. Yonatan Belinkov. 2018. On internal language repre- sentations in deep learning: An analysis of machine translation and speech recognition. Ph.D. thesis, Massachusetts Institute of Technology.
  7. Yonatan Belinkov. 2022. Probing classifiers: Promises, shortcomings, and advances. Computational Linguis- tics, 48(1):207-219.
  8. Joshua Bensemann, Alex Peng, Diana Benavides-Prado, Yang Chen, Neset Tan, Paul Michael Corballis, Patri- cia Riddle, and Michael Witbrock. 2022. Eye gaze and self-attention: How humans and transformers attend words in sentences. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 75-87, Dublin, Ireland. Associa- tion for Computational Linguistics.
  9. Leonard Bereska and Stratis Gavves. 2024. Mechanistic interpretability for AI safety -a review. Transactions on Machine Learning Research.
  10. Joost Broekens, Bernhard Hilpert, Suzan Verberne, Kim Baraka, Patrick Gebhard, and Aske Plaat. 2023. Fine- grained affective processing capabilities emerging from large language models. In 2023 11th Interna- tional Conference on Affective Computing and Intel- ligent Interaction (ACII), pages 1-8. IEEE.
  11. Tobias Brosch and David Sander. 2013. Comment: the appraising brain: towards a neuro-cognitive model of appraisal processes in emotion. Emotion Review, 5(2):163-168.
  12. Stephen Casper, Carson Ezell, Charlotte Siegmann, Noam Kolt, Taylor Lynn Curtis, Benjamin Bucknall, Andreas Haupt, Kevin Wei, Jérémy Scheurer, Marius Hobbhahn, et al. 2024. Black-box access is insuffi- cient for rigorous ai audits. In The 2024 ACM Confer- ence on Fairness, Accountability, and Transparency, pages 2254-2272.
  13. Angelica Chen, Ravid Shwartz-Ziv, Kyunghyun Cho, Matthew L Leavitt, and Naomi Saphra. 2024. Sudden drops in the loss: Syntax acquisition, phase transi- tions, and simplicity bias in MLMs. In The Twelfth International Conference on Learning Representa- tions.
  14. Kevin Clark, Urvashi Khandelwal, Omer Levy, and Christopher D. Manning. 2019. What does BERT look at? an analysis of BERT's attention. In Pro- ceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 276-286, Florence, Italy. Association for Com- putational Linguistics.
  15. Arthur Conmy, Augustine Mavor-Parker, Aengus Lynch, Stefan Heimersheim, and Adrià Garriga-Alonso. 2023. Towards automated circuit discovery for mech- anistic interpretability. Advances in Neural Informa- tion Processing Systems, 36:16318-16352.
  16. Alexis Conneau, German Kruszewski, Guillaume Lam- ple, Loïc Barrault, and Marco Baroni. 2018. What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties. In Proceedings of the 56th Annual Meeting of the As- sociation for Computational Linguistics (Volume 1: Long Papers), pages 2126-2136, Melbourne, Aus- tralia. Association for Computational Linguistics.
  17. Oliver Eberle, Stephanie Brandl, Jonas Pilot, and An- ders Søgaard. 2022. Do transformer models show similar attention patterns to task-specific human gaze? In Proceedings of the 60th Annual Meet- ing of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4295-4309, Dublin, Ireland. Association for Computational Linguistics.
  18. Phoebe C Ellsworth and Klaus R Scherer. 2003. Ap- praisal processes in emotion. Oxford University Press.
  19. Joshua Engels, Eric J Michaud, Isaac Liao, Wes Gurnee, and Max Tegmark. 2025. Not all language model features are linear. In The Thirteenth International Conference on Learning Representations.
  20. Allyson Ettinger, Ahmed Elgohary, and Philip Resnik. 2016. Probing for semantic evidence of composition by means of simple classification tasks. In Proceed- ings of the 1st workshop on evaluating vector-space representations for nlp, pages 134-139.
  21. Jiahai Feng, Stuart Russell, and Jacob Steinhardt. 2025. Monitoring latent world states in language models with propositional probes. In The Thirteenth Interna- tional Conference on Learning Representations.
  22. Nico H Frijda, Peter Kuipers, and Elisabeth Ter Schure. 1989. Relations among emotion, appraisal, and emo- tional action readiness. Journal of personality and social psychology, 57(2):212.
  23. Chris Gagne and Peter Dayan. 2023. The in- ner sentiments of a thought. arXiv preprint arXiv:2307.01784. · arXiv
  24. Mor Geva, Avi Caciularu, Kevin Wang, and Yoav Gold- berg. 2022. Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Process- ing, pages 30-45, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  25. Asma Ghandeharioun, Avi Caciularu, Adam Pearce, Lu- cas Dixon, and Mor Geva. 2024. Patchscopes: A unifying framework for inspecting hidden representa- tions of language models. In Forty-first International Conference on Machine Learning.
  26. Mario Giulianelli, Jack Harding, Florian Mohnert, Dieuwke Hupkes, and Willem Zuidema. 2018. Under the hood: Using diagnostic classifiers to investigate and improve how language models track agreement information. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 240-248, Brussels, Belgium. Association for Computational Linguistics.
  27. Abhijeet Gupta, Gemma Boleda, Marco Baroni, and Sebastian Padó. 2015. Distributional vectors encode referential attributes. In Proceedings of the 2015 Conference on Empirical Methods in Natural Lan- guage Processing, pages 12-21, Lisbon, Portugal. Association for Computational Linguistics.
  28. Michael Hanna, Ollie Liu, and Alexandre Variengien. 2023. How does GPT-2 compute greater-than?: In- terpreting mathematical abilities in a pre-trained lan- guage model. In Thirty-seventh Conference on Neu- ral Information Processing Systems.
  29. Stefan Heimersheim and Neel Nanda. 2024. How to use and interpret activation patching. arXiv preprint arXiv:2404.15255. · arXiv
  30. John Hewitt and Percy Liang. 2019. Designing and in- terpreting probes with control tasks. In Proceedings of the 2019 Conference on Empirical Methods in Nat- ural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2733-2743, Hong Kong, China. Association for Computational Linguistics.
  31. Dieuwke Hupkes and Willem Zuidema. 2018. Visualisa- tion and 'diagnostic classifiers' reveal how recurrent and recursive neural networks process hierarchical structure. In Proceedings of the Twenty-Seventh Inter- national Joint Conference on Artificial Intelligence, IJCAI-18, pages 5617-5621. International Joint Con- ferences on Artificial Intelligence Organization.
  32. Guangyuan Jiang, Manjie Xu, Song-Chun Zhu, Wen- juan Han, Chi Zhang, and Yixin Zhu. 2023. Evaluat- ing and inducing personality in pre-trained language models. In NeurIPS.
  33. Hang Jiang, Xiajie Zhang, Xubo Cao, Cynthia Breazeal, Deb Roy, and Jad Kabbara. 2024a. PersonaLLM: Investigating the ability of large language models to express personality traits. In Findings of the Associ- ation for Computational Linguistics: NAACL 2024, pages 3605-3627, Mexico City, Mexico. Association for Computational Linguistics.
  34. Yibo Jiang, Bryon Aragam, and Victor Veitch. 2024b. Uncovering meanings of embeddings via partial or- thogonality. Advances in Neural Information Pro- cessing Systems, 36.
  35. Akos Kádár, Grzegorz Chrupała, and Afra Alishahi. 2017. Representation of linguistic form and func- tion in recurrent neural networks. Computational Linguistics, 43(4):761-780.
  36. Arne Köhn. 2015. What's in an embedding? analyzing word embeddings through multilingual evaluation. In Proceedings of the 2015 Conference on Empiri- cal Methods in Natural Language Processing, pages 2067-2073, Lisbon, Portugal. Association for Com- putational Linguistics.
  37. Philip A Kragel, David Sander, and Kevin S LaBar. 2024. Can brain data be used to arbitrate among emotion theories? In Emotion theory: The Routledge comprehensive guide, pages 511-542. Routledge.
  38. Sreejan Kumar, Theodore R Sumers, Takateru Ya- makoshi, Ariel Goldstein, Uri Hasson, Kenneth A Norman, Thomas L Griffiths, Robert D Hawkins, and Samuel A Nastase. 2024. Shared functional special- ization in transformer-based language models and the human brain. Nature communications, 15(1):5523.
  39. Elisa Kwon, John D Patterson, Roger E Beaty, and Kosa Goucher-Lambert. 2024. Assessing the alignment between word representations in the brain and large language models. In International Conference on- Design Computing and Cognition, pages 207-223. Springer.
  40. Richard S Lazarus. 1991. Emotion and adaptation. Ox- ford University Press on Demand.
  41. Joana Leitão, Ben Meuleman, Dimitri Van De Ville, and Patrik Vuilleumier. 2020. Computational imag- ing during video game playing shows dynamic syn- chronization of cortical and subcortical networks of emotions. PLoS biology, 18(11):e3000900.
  42. Omer Levy and Yoav Goldberg. 2014. Linguistic regu- larities in sparse and explicit word representations. In Proceedings of the eighteenth conference on compu- tational natural language learning, pages 171-180.
  43. Belinda Z. Li, Maxwell Nye, and Jacob Andreas. 2021. Implicit representations of meaning in neural lan- guage models. In Proceedings of the 59th Annual Meeting of the Association for Computational Lin- guistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1813-1827, Online. Association for Computational Linguistics.
  44. Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. 2023. Inference- time intervention: Eliciting truthful answers from a language model. In Thirty-seventh Conference on Neural Information Processing Systems.
  45. Tom Lieberum, Matthew Rahtz, János Kramár, Neel Nanda, Geoffrey Irving, Rohin Shah, and Vladimir Mikulik. 2023. Does circuit analysis interpretability scale? evidence from multiple choice capabilities in chinchilla. arXiv preprint arXiv:2307.09458. · arXiv
  46. Xin Liu, Ziyue Zhang, and Jingxin Nie. 2025. Talking to the brain: Using large language models as proxies to model brain semantic representation. Preprint, arXiv:2502.18725. · arXiv
  47. Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associ- ations in gpt. Advances in Neural Information Pro- cessing Systems, 35:17359-17372.
  48. Tomas Mikolov, Quoc V Le, and Ilya Sutskever. 2013a. Exploiting similarities among languages for machine translation. arXiv preprint arXiv:1309.4168. · arXiv
  49. Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. 2013b. Linguistic regularities in continuous space word representations. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 746-751, Atlanta, Georgia. Association for Computational Linguistics.
  50. Agnes Moors. 2013. On the causal role of appraisal in emotion. Emotion Review, 5(2):132-140.
  51. Neel Nanda, Andrew Lee, and Martin Wattenberg. 2023. Emergent linear representations in world models of self-supervised sequence models. In Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, Singapore. Association for Computational Linguistics.
  52. Team OLMo, Pete Walsh, Luca Soldaini, Dirk Groen- eveld, Kyle Lo, Shane Arora, Akshita Bhagia, Yuling Gu, Shengyi Huang, Matt Jordan, et al. 2024. 2 olmo 2 furious. arXiv preprint arXiv:2501.00656. · arXiv
  53. Catherine Olsson, Nelson Elhage, Neel Nanda, Nicholas Joseph, Nova DasSarma, Tom Henighan, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, et al. 2022. In-context learning and induction heads. arXiv preprint arXiv:2209.11895. · arXiv
  54. Andrew Ortony, Gerald L Clore, and Allan Collins. 2022. The cognitive structure of emotions. Cam- bridge university press.
  55. Kiho Park, Yo Joong Choe, and Victor Veitch. 2024. The linear representation hypothesis and the geome- try of large language models. In International con- ference on machine learning, ICML'24. JMLR.org.
  56. Matthew E. Peters, Mark Neumann, Luke Zettlemoyer, and Wen-tau Yih. 2018. Dissecting contextual word embeddings: Architecture and representation. In Pro- ceedings of the 2018 Conference on Empirical Meth- ods in Natural Language Processing, pages 1499- 1509, Brussels, Belgium. Association for Computa- tional Linguistics.
  57. Nikolay B Petrov, Gregory Serapio-García, and Jason Rentfrow. 2024. Limited ability of llms to simulate human psychological behaviours: a psychometric analysis. arXiv preprint arXiv:2405.07248. · arXiv
  58. Daking Rai, Yilun Zhou, Shi Feng, Abulhair Saparov, and Ziyu Yao. 2024. A practical review of mecha- nistic interpretability for transformer-based language models. arXiv preprint arXiv:2407.02646. · arXiv
  59. I Rosenman and C Smith. 2001. Appraisal theory: Overview, assumptions, varieties, controversies. Ap- praisal processes in emotion. Theory, methods, re- search, pages 3-19.
  60. Klaus R Scherer et al. 1984. On the nature and function of emotion: A component process approach. Ap- proaches to emotion, 2293(317):31.
  61. Ashish Sharma, Kevin Rushton, Inna Lin, David Wad- den, Khendra Lucas, Adam Miner, Theresa Nguyen, and Tim Althoff. 2023. Cognitive reframing of nega- tive thoughts through human-language model inter- action. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers), pages 9977-10000, Toronto, Canada. Association for Computational Linguistics.
  62. Xing Shi, Inkit Padhi, and Kevin Knight. 2016. Does string-based neural MT learn source syntax? In Pro- ceedings of the 2016 Conference on Empirical Meth- ods in Natural Language Processing, pages 1526- 1534, Austin, Texas. Association for Computational Linguistics.
  63. Craig A Smith and Phoebe C Ellsworth. 1985. Pat- terns of cognitive appraisal in emotion. Journal of personality and social psychology, 48(4):813.
  64. Craig A Smith and Leslie D Kirby. 2011. The role of appraisal and emotion in coping and adaptation. The handbook of stress science: Biology, psychology, and health, pages 195-208.
  65. Joseph Suh, Suhong Moon, Minwoo Kang, and David Chan. 2024. Rediscovering the latent dimensions of personality with large language models as trait de- scriptors. In NeurIPS 2024 Workshop on Behavioral Machine Learning.
  66. Ala N. Tak and Jonathan Gratch. 2023. Is GPT a Computational Model of Emotion? . In 2023 11th In- ternational Conference on Affective Computing and Intelligent Interaction (ACII), pages 1-8, Los Alami- tos, CA, USA. IEEE Computer Society.
  67. Ian Tenney, Dipanjan Das, and Ellie Pavlick. 2019a. BERT rediscovers the classical NLP pipeline. In Proceedings of the 57th Annual Meeting of the Asso- ciation for Computational Linguistics, pages 4593- 4601, Florence, Italy. Association for Computational Linguistics.
  68. Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R Thomas McCoy, Najoung Kim, Ben- jamin Van Durme, Sam Bowman, Dipanjan Das, and Ellie Pavlick. 2019b. What do you learn from con- text? probing for sentence structure in contextualized word representations. In International Conference on Learning Representations.
  69. Eric Todd, Millicent Li, Arnab Sen Sharma, Aaron Mueller, Byron C Wallace, and David Bau. 2024. Function vectors in large language models. In The Twelfth International Conference on Learning Repre- sentations.
  70. Enrica Troiano, Laura Oberländer, and Roman Klinger. 2023. Dimensional modeling of emotions in text with appraisal theories: Corpus creation, annotation reliability, and prediction. Computational Linguis- tics, 49(1):1-72.
  71. Alexander Matt Turner, Lisa Thiergart, Gavin Leech, David Udell, Juan J Vazquez, Ulisse Mini, and Monte MacDiarmid. 2023. Activation addition: Steering language models without optimization. arXiv e- prints, pages arXiv-2308.
  72. Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Yaron Singer, and Stuart Shieber. 2020. Investigating gender bias in language models using causal mediation analysis. Advances in neural information processing systems, 33:12388- 12401.
  73. Kevin Ro Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, and Jacob Steinhardt. 2023a. Inter- pretability in the wild: a circuit for indirect object identification in GPT-2 small. In The Eleventh Inter- national Conference on Learning Representations.
  74. Xuena Wang, Xueting Li, Zi Yin, Yue Wu, and Jia Liu. 2023b. Emotional intelligence of large lan- guage models. Journal of Pacific Rim Psychology, 17:18344909231213958.
  75. Joshua Wondra and Phoebe Ellsworth. 2015. An ap- praisal theory of empathy and other vicarious emo- tional experiences. Psychological review, 122.
  76. Nutchanon Yongsatianchot, Parisa Ghanad Torshizi, and Stacy Marsella. 2023. Investigating large language models' perception of emotion using appraisal the- ory. In 2023 11th International Conference on Af- fective Computing and Intelligent Interaction Work- shops and Demos (ACIIW), pages 1-8. IEEE.
  77. Weixiang Zhao, Yanyan Zhao, Xin Lu, Shilong Wang, Yanpeng Tong, and Bing Qin. 2023. Is chat- gpt equipped with emotional dialogue capabilities? arXiv preprint arXiv:2304.09582. · arXiv

Cited by

Sorted by citations

Metadata

Authors
Tak, A. N., Banayeeanzade, A., Bolourani, A., Kian, M., Jia, R., & Gratch, J.
Affiliations
  • University of Southern California (US)
  • University of California, Los Angeles (US)
ORCID
Venue
Findings of the Association for Computational Linguistics: ACL 2025
Publisher
Association for Computational Linguistics
Published
2025
Pages
13090-13120
DOI
10.18653/v1/2025.findings-acl.679
OpenAlex
W4412888258
Cited by
12
References
0
Citations by year
2026: 8 · 2025: 4
FWCI
17.87
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Findings of the Association for Computational Linguistics: ACL (Findings of ACL) (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Funders
Army Research Office (W911NF)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
Keywords
emotion inference, large language models, mechanistic interpretability, functional localization, appraisal theory, causal intervention, emotion representation

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