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.
arXiv preprint arXiv:2310.03051 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
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.
Improvements in LLM Theory of Mind on static benchmarks do not reliably improve performance in dynamic, first-person human-AI interactions across goal-oriented and experience-oriented tasks.
AVISE provides a new framework and automated SET that identifies jailbreak vulnerabilities in language models with 92% accuracy, finding all nine tested models vulnerable to an augmented Red Queen attack.
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
citing papers explorer
-
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.
-
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.
-
Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations
Improvements in LLM Theory of Mind on static benchmarks do not reliably improve performance in dynamic, first-person human-AI interactions across goal-oriented and experience-oriented tasks.
-
AVISE: Framework for Evaluating the Security of AI Systems
AVISE provides a new framework and automated SET that identifies jailbreak vulnerabilities in language models with 92% accuracy, finding all nine tested models vulnerable to an augmented Red Queen attack.
-
GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.