Summary of Grounding Language About Belief in a Bayesian Theory-of-mind, by Lance Ying et al.
Grounding Language about Belief in a Bayesian Theory-of-Mind
by Lance Ying, Tan Zhi-Xuan, Lionel Wong, Vikash Mansinghka, Joshua Tenenbaum
First submitted to arxiv on: 16 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed framework grounds the semantics of belief statements in a Bayesian theory-of-mind, modeling how humans jointly infer coherent sets of goals, beliefs, and plans that explain an agent’s actions. This 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. The authors 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. By comparing the results to pure logical deduction, non-mentalizing baselines, and mentalizing that ignores the role of instrumental plans, the study demonstrates the importance of theory-of-mind for a semantics of belief. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Beliefs are tricky things – we can’t see them directly, but we talk about what others think and know all the time. Why can we do this? To answer this question, researchers came up with a new way to understand how our brains work when we try to figure out what someone else is thinking or doing. They created a special kind of math that helps us make sense of other people’s actions and goals. The study showed that this way of thinking – called “theory-of-mind” – helps us understand why we can talk about what others believe, and how our brains work when we’re trying to figure out what someone else is thinking. |
Keywords
» Artificial intelligence » Semantics
