MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks
Cristian-Paul Bara, Sky CH-Wang, Joyce Chai
Abstract
An ideal integration of autonomous agents in a human world implies that they are able to collaborate on human terms. In particular, theory of mind plays an important role in maintaining common ground during human collaboration and communication. To enable theory of mind modeling in situated interactions, we introduce a fine-grained dataset of collaborative tasks performed by pairs of human subjects in the 3D virtual blocks world of Minecraft. It provides information that captures partners' beliefs of the world and of each other as an interaction unfolds, bringing abundant opportunities to study human collaborative behaviors in situated language communication. As a first step towards our goal of developing embodied AI agents able to infer belief states of collaborative partners in situ, we build and present results on computational models for several theory of mind tasks.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers17
- Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMsMaarten Sap, Ronan Le Bras, Daniel Fried, Yejin ChoiEMNLP 2022 · 92 citations
- Learning to Model the World With LanguageJessy Lin, Yuqing Du, Olivia Watkins, Danijar Hafner et al.ICML 2024 · 76 citations
- Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief TrackerMelanie Sclar, Sachin Kumar, Peter West, Alane Suhr et al.ACL 2023 · 21 citations
- A Framework for Learning to Request Rich and Contextually Useful Information from HumansKhanh X. Nguyen, Yonatan Bisk, Hal Daumé IIIICML 2022 · 21 citations
- Navigating Rifts in Human-LLM Grounding: Study and BenchmarkOmar Shaikh, Hussein Mozannar, Gagan Bansal, Adam Fourney et al.ACL 2025 · 21 citations
Builds on3
- Towards Mutual Theory of Mind in Human-AI Interaction: How Language Reflects What Students Perceive About a Virtual Teaching AssistantQiaosi Wang, Koustuv Saha, Eric Gregori, David A. Joyner et al.CHI 2021 · 115 citations
- Learning to execute instructions in a Minecraft dialoguePrashant Jayannavar, Anjali Narayan-Chen, Julia HockenmaierACL 2020 · 22 citations
- An Annotated Corpus of Reference Resolution for Interpreting Common GroundingTakuma Udagawa, Akiko AizawaAAAI 2020 · 10 citations
Related papers
- Few-shot Language Coordination by Modeling Theory of MindHao Zhu, Graham Neubig, Yonatan BiskICML 2021 · 43 citations
- CraftAssist Instruction Parsing: Semantic Parsing for a Voxel-World AssistantKavya Srinet, Yacine Jernite, Jonathan Gray, Arthur SzlamACL 2020 · 7 citations
- Theory of Mind for Multi-Agent Collaboration via Large Language ModelsHuao Li, Yu Quan Chong, Simon Stepputtis, Joseph Campbell et al.EMNLP 2023 · 57 citations
- SIMMC-VR: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive VR StreamsTe-Lin Wu, Satwik Kottur, Andrea Madotto, Mahmoud Azab et al.ACL 2023 · 4 citations
- Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan AcquisitionMatteo Bortoletto, Constantin Ruhdorfer, Adnen Abdessaied, Lei Shi et al.ACL 2024
