Year: 2026
Type: conference-paper
Abstract: Theory of Mind (ToM), the ability to infer others' mental states from behavior, is pivotal for developing machines with human-level social intelligence.Existing methods endowing LLMs with ToM fall into two paradigms: training-free methods and those repurposing ToM evaluation benchmarks as training data for RL-based fine-tuning.However, training-free methods fail to internalize the augmented ToM into the LLMs.Meanwhile, using evaluation benchmarks as training sources is conceptually problematic and, in practice, results in narrow in-domain overfitting rather than robust ToM.To address the lack of training resources within the ToM community and to empower LLMs with robust ToM, we introduce ToM-Synth, a factorial combinatorial synthesis framework of 6912 social units.This framework enables the systematic synthesis of ToM data, yielding a training dataset of 27,648 instances, termed ToM-Synth-27K.Utilizing ToM-Synth-27K for RL fine-tuning, experimental results demonstrate consistent and significant improvements across models of varying families and scales on ToM, Emotional Intelligence, and Social Commonsense benchmarks.Furthermore, we observe concurrent enhancements in IQ-related tasks (math, science, logic) and effective performance scaling with increasing data scale.
Language: English
Subfield: Developmental and Educational Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: hybrid
Award: G7036249533
OpenAlex ID: W7166861458