Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker
Authors:
- Melanie SclarMSMelanie Sclar
- Peter WestPWPeter West
- Yulia TsvetkovYTYulia Tsvetkov
Preprint
Abstract
Theory of Mind (ToM)$\unicode{x2014}$the ability to reason about the mental states of other people$\unicode{x2014}$is a key element of our social intelligence. Yet, despite their ever more impressive performance, large-scale neural language models still lack basic theory of mind capabilities out-of-the-box. We posit that simply scaling up models will not imbue them with theory of mind due to the inherently symbolic and implicit nature of the phenomenon, and instead investigate an alternative: can we design a decoding-time algorithm that enhances theory of mind of off-the-shelf neural language models without explicit supervision? We present SymbolicToM, a plug-and-play approach to reason about the belief states of multiple characters in reading comprehension tasks via explicit symbolic representation. More concretely, our approach tracks each entity's beliefs, their estimation of other entities' beliefs, and higher-order levels of reasoning, all through graphical representations, allowing for more precise and interpretable reasoning than previous approaches. Empirical results on the well-known ToMi benchmark (Le et al., 2019) demonstrate that SymbolicToM dramatically enhances off-the-shelf neural networks' theory of mind in a zero-shot setting while showing robust out-of-distribution performance compared to supervised baselines. Our work also reveals spurious patterns in existing theory of mind benchmarks, emphasizing the importance of out-of-distribution evaluation and methods that do not overfit a particular dataset.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Human-level play in the game ofDiplomacyby combining language models with strategic reasoningScience, 2022
- CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition modelsiScience, 2021
- Advanced theory of mind in adolescence: Do age, gender and friendship style play a role?Journal of Adolescence, 2017
- Scaling of Advanced Theory-of-Mind TasksChild Development, 2016
- When narrative takes over: The representation of embedded mindstates in Shakespeare’s OthelloLanguage and Literature: International Journal of Stylistics, 2015
- Core mechanisms in ‘theory of mind’Trends in Cognitive Sciences, 2004
- Development and neurophysiology of mentalizingPhilosophical Transactions of the Royal Society B: Biological Sciences, 2003
- Does the autistic child have a “theory of mind” ?Cognition, 1985
- Beliefs about beliefs: Representation and constraining function of wrong beliefs in young children's understanding of deceptionCognition, 1983
- Does the chimpanzee have a theory of mind?Behavioral and Brain Sciences, 1978