RecToM recursively constructs character perspectives to reduce higher-order ToM questions to first-person questions, reaching 100% accuracy on Hi-ToM and SOTA on Big-ToM and FanToM across LLM backbones.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mind the Perspective: Let's Reason Recursively for Theory of Mind
RecToM recursively constructs character perspectives to reduce higher-order ToM questions to first-person questions, reaching 100% accuracy on Hi-ToM and SOTA on Big-ToM and FanToM across LLM backbones.