An autonomous debating system
- PMID: 33731946
- DOI: 10.1038/s41586-021-03215-w
An autonomous debating system
Abstract
Artificial intelligence (AI) is defined as the ability of machines to perform tasks that are usually associated with intelligent beings. Argument and debate are fundamental capabilities of human intelligence, essential for a wide range of human activities, and common to all human societies. The development of computational argumentation technologies is therefore an important emerging discipline in AI research1. Here we present Project Debater, an autonomous debating system that can engage in a competitive debate with humans. We provide a complete description of the system's architecture, a thorough and systematic evaluation of its operation across a wide range of debate topics, and a detailed account of the system's performance in its public debut against three expert human debaters. We also highlight the fundamental differences between debating with humans as opposed to challenging humans in game competitions, the latter being the focus of classical 'grand challenges' pursued by the AI research community over the past few decades. We suggest that such challenges lie in the 'comfort zone' of AI, whereas debating with humans lies in a different territory, in which humans still prevail, and for which novel paradigms are required to make substantial progress.
Comment in
-
Argument technology for debating with humans.Nature. 2021 Mar;591(7850):373-374. doi: 10.1038/d41586-021-00539-5. Nature. 2021. PMID: 33731943 No abstract available.
-
Am I arguing with a machine? AI debaters highlight need for transparency.Nature. 2021 Apr;592(7853):166. doi: 10.1038/d41586-021-00867-6. Nature. 2021. PMID: 33828323 No abstract available.
Similar articles
-
Artificial intelligence: A joint narrative on potential use in pediatric stem and immune cell therapies and regenerative medicine.Transfus Apher Sci. 2018 Jun;57(3):422-424. doi: 10.1016/j.transci.2018.05.004. Epub 2018 May 9. Transfus Apher Sci. 2018. PMID: 29784537 Review.
-
Multi-AI competing and winning against humans in iterated Rock-Paper-Scissors game.Sci Rep. 2020 Aug 17;10(1):13873. doi: 10.1038/s41598-020-70544-7. Sci Rep. 2020. PMID: 32807813 Free PMC article.
-
Legal, regulatory, and ethical frameworks for development of standards in artificial intelligence (AI) and autonomous robotic surgery.Int J Med Robot. 2019 Feb;15(1):e1968. doi: 10.1002/rcs.1968. Int J Med Robot. 2019. PMID: 30397993 Review.
-
The debate over understanding in AI's large language models.Proc Natl Acad Sci U S A. 2023 Mar 28;120(13):e2215907120. doi: 10.1073/pnas.2215907120. Epub 2023 Mar 21. Proc Natl Acad Sci U S A. 2023. PMID: 36943882 Free PMC article.
-
Dignity and Dissent in Humans and Non-humans.Sci Eng Ethics. 2020 Oct;26(5):2497-2510. doi: 10.1007/s11948-020-00245-x. Sci Eng Ethics. 2020. PMID: 32601831
Cited by
-
An AI-Based Curling Game System for Winter Olympics.Research (Wash D C). 2022 Oct 20;2022:9805054. doi: 10.34133/2022/9805054. eCollection 2022. Research (Wash D C). 2022. PMID: 36349338 Free PMC article.
-
Nobel Turing Challenge: creating the engine for scientific discovery.NPJ Syst Biol Appl. 2021 Jun 18;7(1):29. doi: 10.1038/s41540-021-00189-3. NPJ Syst Biol Appl. 2021. PMID: 34145287 Free PMC article. Review.
-
LLM-generated messages can persuade humans on policy issues.Nat Commun. 2025 Jul 1;16(1):6037. doi: 10.1038/s41467-025-61345-5. Nat Commun. 2025. PMID: 40593786 Free PMC article.
-
Why a Virtual Assistant for Moral Enhancement When We Could have a Socrates?Sci Eng Ethics. 2021 Jun 29;27(4):42. doi: 10.1007/s11948-021-00318-5. Sci Eng Ethics. 2021. PMID: 34189623 Free PMC article.
-
Usability and Credibility of a COVID-19 Vaccine Chatbot for Young Adults and Health Workers in the United States: Formative Mixed Methods Study.JMIR Hum Factors. 2023 Jan 30;10:e40533. doi: 10.2196/40533. JMIR Hum Factors. 2023. PMID: 36409300 Free PMC article.
References
-
- Lawrence, J. & Reed, C. Argument mining: a survey. Comput. Linguist. 45, 765–818 (2019). - DOI
-
- Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. Preprint at https://arxiv.org/abs/1810.04805 (2018).
-
- Peters, M. et al. Deep contextualized word representations. In Proc. 2018 Conf. North Am. Ch. Assoc. for Computational Linguistics: Human Language Technologies Vol. 1, 2227–2237 (Association for Computational Linguistics, 2018); https://www.aclweb.org/anthology/N18–1202
-
- Radford, A. et al. Language models are unsupervised multitask learners. OpenAI Blog 1, http://www.persagen.com/files/misc/radford2019language.pdf (2019).
-
- Socher, R. et al. Recursive deep models for semantic compositionality over a sentiment treebank. In Proc. Empirical Methods in Natural Language Processing (EMNLP) 1631–1642 (Association for Computational Linguistics, 2013).
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Miscellaneous