# Grounding Language about Belief in a Bayesian Theory-of-Mind

arXiv: https://arxiv.org/abs/2402.10416 · HTML: https://mlsanity.com/paper/2402.10416/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Builds on (most cited first, 8 of 8)

- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought](https://mlsanity.com/paper/2306.12672/) (2023)
- [Online Bayesian Goal Inference for Boundedly-Rational Planning Agents](https://mlsanity.com/paper/2006.07532/) (2020)
- [The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs](https://mlsanity.com/paper/2306.14325/) (2023)
- [Inferring the Goals of Communicating Agents from Actions and Instructions](https://mlsanity.com/paper/2306.16207/) (2023)
- [A Gentle Introduction to Epistemic Planning: The DEL Approach](https://mlsanity.com/paper/1703.02192/) (2017)
- [Efficient Multi-agent Epistemic Planning: Teaching Planners About Nested Belief](https://mlsanity.com/paper/2110.02480/) (2021)
- [Satisficing Mentalizing: Bayesian Models of Theory of Mind Reasoning in Scenarios with Different Uncertainties](https://mlsanity.com/paper/1909.10419/) (2019)

## Built on by (most cited first, 8 of 8)

- [Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models](https://mlsanity.com/paper/2503.17523/) (2025)
- [GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment](https://mlsanity.com/paper/2403.11075/) (2024)
- [Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People](https://mlsanity.com/paper/2510.20886/) (2025)
- [Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind](https://mlsanity.com/paper/2408.12022/) (2024)
- [Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner](https://mlsanity.com/paper/2506.01301/) (2025)
- [HugAgent: A Human Simulation Benchmark for Individual-Level Reasoning](https://mlsanity.com/paper/2510.15144/) (2025)
- [Modeling the Mental World for Embodied AI: A Comprehensive Review](https://mlsanity.com/paper/2601.02378/) (2025)
- [Belief Attribution as Mental Explanation: The Role of Accuracy, Informativity, and Causality](https://mlsanity.com/paper/2505.19376/) (2025)

## Abstract (arXiv)

Despite the fact that beliefs are mental states that cannot be directly observed, humans talk about each others' beliefs on a regular basis, often using rich compositional language to describe what others think and know. What explains this capacity to interpret the hidden epistemic content of other minds? In this paper, we take a step towards an answer by grounding the semantics of belief statements in a Bayesian theory-of-mind: By modeling how humans jointly infer coherent sets of goals, beliefs, and plans that explain an agent's actions, then evaluating statements about the agent's beliefs against these inferences via epistemic logic, our framework provides a conceptual role semantics for belief, explaining the gradedness and compositionality of human belief attributions, as well as their intimate connection with goals and plans. We evaluate this framework by studying how humans attribute goals and beliefs while watching an agent solve a doors-and-keys gridworld puzzle that requires instrumental reasoning about hidden objects. In contrast to pure logical deduction, non-mentalizing baselines, and mentalizing that ignores the role of instrumental plans, our model provides a much better fit to human goal and belief attributions, demonstrating the importance of theory-of-mind for a semantics of belief.