User-turn generation reveals that LLMs' interaction awareness is largely decoupled from task accuracy, remaining near zero in deterministic settings even as accuracy scales to 96.8% on GSM8K.
arXiv preprint arXiv:2410.13648 , year =
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
Introduces NCP-ExploreToM framework to evaluate LLMs on inducing belief states via planning and action, with GPT-5 succeeding on ~80% of tasks and outperforming humans.
GroupToM-Bench is presented as the first multimodal benchmark for group-level Theory of Mind spanning micro BDI states to macro outcome prediction, with experiments showing current MLLMs lag human baselines on nonlinear social dynamics.
CogWM is a new LLM user model for evaluating social influence by predicting and tracking cognitive state evolution in dialogues, trained on 150k samples and shown to differentiate AI agents effectively.
EnactToM is an evolving benchmark of embodied multi-agent tasks that tests functional Theory of Mind by requiring agents to act optimally on implicit beliefs in partially observable 3D environments.
Suggestive evidence indicates language models develop interconnected social world models by functionally integrating theory of mind and pragmatic reasoning.
citing papers explorer
-
Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models
User-turn generation reveals that LLMs' interaction awareness is largely decoupled from task accuracy, remaining near zero in deterministic settings even as accuracy scales to 96.8% on GSM8K.
-
Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action
Introduces NCP-ExploreToM framework to evaluate LLMs on inducing belief states via planning and action, with GPT-5 succeeding on ~80% of tasks and outperforming humans.
-
GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs
GroupToM-Bench is presented as the first multimodal benchmark for group-level Theory of Mind spanning micro BDI states to macro outcome prediction, with experiments showing current MLLMs lag human baselines on nonlinear social dynamics.
-
Cognitive World Models for Process-Level Social Influence Evaluation
CogWM is a new LLM user model for evaluating social influence by predicting and tracking cognitive state evolution in dialogues, trained on 150k samples and shown to differentiate AI agents effectively.
-
EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents
EnactToM is an evolving benchmark of embodied multi-agent tasks that tests functional Theory of Mind by requiring agents to act optimally on implicit beliefs in partially observable 3D environments.
-
On Emergent Social World Models -- Evidence for Functional Integration of Theory of Mind and Pragmatic Reasoning in Language Models
Suggestive evidence indicates language models develop interconnected social world models by functionally integrating theory of mind and pragmatic reasoning.