What if large language models could not only infer human mindsets but also expose every blind spot in team dialogue such as discrepancies in the team members' joint understanding? We present a novel, two-step framework that leverages large language models (LLMs) both as human-style annotators of team dialogues to track the team's shared mental models (SMMs) and as automated discrepancy detectors among individuals' mental states. In the first step, an LLM generates annotations by identifying SMM elements within task-oriented dialogues from the Cooperative Remote Search Task (CReST) corpus. Then, a secondary LLM compares these LLM-derived annotations and human annotations against gold-standard labels to detect and characterize divergences. We define an SMM coherence evaluation framework for this use case and apply it to six CReST dialogues, ultimately producing: (1) a dataset of human and LLM annotations; (2) a reproducible evaluation framework for SMM coherence; and (3) an empirical assessment of LLM-based discrepancy detection. Our results reveal that, although LLMs exhibit apparent coherence on straightforward natural-language annotation tasks, they systematically err in scenarios requiring spatial reasoning or disambiguation of prosodic cues.
Humans typically use natural language to update teammates on task states. Since not all updates are communicated, discrepancies arise between the team members' mental models that negatively affect overall team performance. How can we categorize such discrepancies? Do misalignments detected in team dialogue predict future mental model misalignments? Traditional shared mental model (SMM) assessment methods rely on retrospective expert coding that cannot capture real-time coordination dynamics. We propose a framework to identify and categorize four types of mental model discrepancies: unsupported beliefs, false beliefs, belief contradictions, and omissions, all of which can naturally emerge in team dialogues. Using dialogues from twenty dyad teams performing collaborative object identification tasks across four sequential levels, we demonstrate that these discrepancy patterns contain predictive signals. Averaging historical discrepancy counts achieves meaningful prediction accuracy using uniform weighting as an exploratory baseline, with differential predictability across discrepancy types.
We introduce DialToM, an annotated Theory of Mind (ToM) benchmark built from naturalistic human-human dialogues using a multiple-choice evaluation framework. Concurrent with recent work showing a gap between explicit mental-state inference and applied ToM in synthetic settings~\cite{gu2024simpletom}, we establish a stricter \emph{State-Driven Diagnostic Probe} in which models must forecast state-consistent dialogue trajectories solely from isolated mental-state profiles without dialogue context. Our evaluation reveals a systematic reasoning asymmetry -- LLMs excel at inferring mental states (Literal ToM) but struggle to leverage them for social forecasting (Functional ToM). Crucially, a domain expert achieves 100% accuracy on this task, proving its validity and establishing a stark human-AI capability gap. Further, a teacher-student reasoning injection probe shows that Gemini 3 Pro -- which establishes the leading baseline -- possesses robust Functional ToM capabilities for context-free forecasting that are transferable to weaker models. DialToM, its evaluation code, and dataset are publicly available at https://github.com/Stealth-py/DialToM.
Text-based evaluations of Theory of Mind (ToM) in Large Language Models (LLMs) often involve cognitive tests akin to the Sally-Anne task that can be gamed due to exposure to relevantly similar tasks in pre-training and do not obviously test models' functional ToM abilities in ways that generalize to naturalistic settings. To address these issues, we introduce the Epistemic Asymmetry Schelling Task (EAST), a two-player dialogue game designed to benchmark robust and generalizable ToM abilities. By requiring LLM-LLM dyads to independently converge on semantic Schelling points under varying states of epistemic transparency, we evaluate whether models can robustly apply ToM to achieve coordination. Our results reveal a significant capability gap in functional social reasoning, with only frontier models successfully navigating the varying epistemic demands of the tasks. Analysis of reasoning traces shows that coordination failures are primarily driven by epistemic tracking errors, such as conflating private knowledge with mutual knowledge. Despite high performance on traditional static benchmarks, our study shows that robust social reasoning and epistemic tracking remain a critical bottleneck, providing concrete targets for future LLM evaluation and development.