Abstract
Theory of Mind (ToM) is a critical component of intelligence but its assessment remains the subject of heated debates. Prior research applied human ToM assessments to natural language processing models using either human-created standardized tests or rule-based templates. However, these methods primarily focus on simplistic reasoning and require further validation. Here, we leverage dynamic epistemic logic to isolate a particular component of ToM and to generate controlled problems. We also introduce new verbalization techniques to express these problems in English natural language. Our findings indicate that some language model scaling (from 70M to 6B and 350M to 174B) does not consistently yield results better than random chance. While GPT-4 demonstrates superior epistemic reasoning capabilities, there is still room for improvement. Our code and datasets are publicly available.- Anthology ID:
- 2023.findings-emnlp.303
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4570–4577
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.303
- DOI:
- 10.18653/v1/2023.findings-emnlp.303
- Cite (ACL):
- Damien Sileo and Antoine Lernould. 2023. MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4570–4577, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic (Sileo & Lernould, Findings 2023)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/2023.findings-emnlp.303.pdf