Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models
This addresses a fundamental cognitive gap in AI for applications requiring social understanding, but it is incremental as it builds on existing ToM benchmarks and methods.
The paper tackles the underperformance of large language models (LLMs) on theory of mind (ToM) benchmarks by evaluating key human ToM precursors, revealing that models perform well in perception inference but poorly in perception-to-belief inference, and introduces PercepToM, a method that significantly enhances LLM performance, especially in false belief scenarios.
While humans naturally develop theory of mind (ToM), the capability to understand other people's mental states and beliefs, state-of-the-art large language models (LLMs) underperform on simple ToM benchmarks. We posit that we can extend our understanding of LLMs' ToM abilities by evaluating key human ToM precursors$-$perception inference and perception-to-belief inference$-$in LLMs. We introduce two datasets, Percept-ToMi and Percept-FANToM, to evaluate these precursory inferences for ToM in LLMs by annotating characters' perceptions on ToMi and FANToM, respectively. Our evaluation of eight state-of-the-art LLMs reveals that the models generally perform well in perception inference while exhibiting limited capability in perception-to-belief inference (e.g., lack of inhibitory control). Based on these results, we present PercepToM, a novel ToM method leveraging LLMs' strong perception inference capability while supplementing their limited perception-to-belief inference. Experimental results demonstrate that PercepToM significantly enhances LLM's performance, especially in false belief scenarios.