Danger Depends on the Mind: A Theory-of-Mind Grounded Dataset and Model for Context-Dependent Dangerous Speech
Year: 2026
Type: conference-paper
Abstract: Dangerous speech detection is a well-studied task, but existing approaches typically treat utterances in isolation, relying on binary labels that ignore who is speaking and in what mental state.We formulate a context-dependent variant of this task by grounding it in Theory-of-Mind (ToM).In cognitive science, ToM studies how humans attribute latent mental states-such as emotions, intentions, and actions-to others.We argue that such states are key signals for assessing the risk of an utterance.Building on this view, we construct ToM-DS, a 79Kinstance dataset where each utterance is paired with structured speaker profiles, ToM states (emotion, intent, action), and topic hierarchies.During data construction, we first identify context-dependent sentences and generate diverse safe and dangerous scenarios surrounding them.High-quality annotations are obtained with state-of-the-art LLMs and a multi-stage cross-agent validation pipeline, yielding a comprehensive and reliable resource for contextdependent dangerous speech detection and fine-grained risk level classification.We further propose ToMGuard, a lightweight model with a dynamic ToM attention mechanism that adaptively weighs different mental-state cues.ToMGuard outperforms strong proprietary and open-source LLMs with significantly fewer parameters.Experimental results show that ToMGuard sets a new benchmark for contextdependent dangerous speech detection and risk level classification on ToM-DS.Our dataset and model are publicly available at https:// github.com/FakerBoom/ToMDS-ToMGGuard.
Institution: Soochow University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G5409605834, G7284123219
OpenAlex ID: W7166827070