Grounding Language about Belief in a Bayesian Theory-of-Mind
- URL: http://arxiv.org/abs/2402.10416v2
- Date: Tue, 9 Jul 2024 01:19:50 GMT
- Title: Grounding Language about Belief in a Bayesian Theory-of-Mind
- Authors: Lance Ying, Tan Zhi-Xuan, Lionel Wong, Vikash Mansinghka, Joshua Tenenbaum,
- Abstract summary: 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, our framework provides a conceptual role semantics for belief.
We evaluate this framework by studying how humans attribute goals and beliefs while watching an agent solve a doors-and-keys gridworld puzzle.
- Score: 5.058204320571824
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Understanding Epistemic Language with a Bayesian Theory of Mind [47.001163099930494]
We introduce a cognitive model of epistemic language interpretation grounded in Bayesian inferences.
We validate our model in an experiment where participants watch an agent navigate a maze to find keys hidden in boxes needed to reach their goal, then rate sentences about the agent's beliefs.
arXiv Detail & Related papers (2024-08-21T22:29:56Z) - Neural embedding of beliefs reveals the role of relative dissonance in human decision-making [6.558951808581431]
We propose a method for extracting nuanced relations between thousands of beliefs by leveraging large-scale user participation data from an online debate platform.
This belief embedding space effectively encapsulates the interconnectedness of diverse beliefs as well as polarization across various social issues.
We find that the relative distance between one existing beliefs and new beliefs can serve as a quantitative estimate of cognitive dissonance.
arXiv Detail & Related papers (2024-08-13T23:58:45Z) - Infinite Ends from Finite Samples: Open-Ended Goal Inference as Top-Down Bayesian Filtering of Bottom-Up Proposals [48.437581268398866]
We introduce a sequential Monte Carlo model of open-ended goal inference.
We validate this model in a goal inference task called Block Words.
Our experiments highlight the importance of uniting top-down and bottom-up models for explaining the speed, accuracy, and generality of human theory-of-mind.
arXiv Detail & Related papers (2024-07-23T18:04:40Z) - The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling
Probabilistic Social Inferences from Linguistic Inputs [50.32802502923367]
We study the process of language driving and influencing social reasoning in a probabilistic goal inference domain.
We propose a neuro-symbolic model that carries out goal inference from linguistic inputs of agent scenarios.
Our model closely matches human response patterns and better predicts human judgements than using an LLM alone.
arXiv Detail & Related papers (2023-06-25T19:38:01Z) - Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play
Multi-Character Belief Tracker [72.09076317574238]
ToM is a plug-and-play approach to investigate the belief states of characters in reading comprehension.
We show that ToM enhances off-the-shelf neural network theory mind in a zero-order setting while showing robust out-of-distribution performance compared to supervised baselines.
arXiv Detail & Related papers (2023-06-01T17:24:35Z) - Intrinsic Physical Concepts Discovery with Object-Centric Predictive
Models [86.25460882547581]
We introduce the PHYsical Concepts Inference NEtwork (PHYCINE), a system that infers physical concepts in different abstract levels without supervision.
We show that object representations containing the discovered physical concepts variables could help achieve better performance in causal reasoning tasks.
arXiv Detail & Related papers (2023-03-03T11:52:21Z) - A Quantitative Symbolic Approach to Individual Human Reasoning [0.0]
We take findings from the literature and show how these, formalized as cognitive principles within a logical framework, can establish a quantitative notion of reasoning.
We employ techniques from non-monotonic reasoning and computer science, namely, a solving paradigm called answer set programming (ASP)
Finally, we can fruitfully use plausibility reasoning in ASP to test the effects of an existing experiment and explain different majority responses.
arXiv Detail & Related papers (2022-05-10T16:43:47Z) - AGENT: A Benchmark for Core Psychological Reasoning [60.35621718321559]
Intuitive psychology is the ability to reason about hidden mental variables that drive observable actions.
Despite recent interest in machine agents that reason about other agents, it is not clear if such agents learn or hold the core psychology principles that drive human reasoning.
We present a benchmark consisting of procedurally generated 3D animations, AGENT, structured around four scenarios.
arXiv Detail & Related papers (2021-02-24T14:58:23Z) - A Qualitative Theory of Cognitive Attitudes and their Change [8.417971913040066]
We show that it allows us to express a variety of relevant concepts for qualitative decision theory.
We also present two extensions of the logic, one by the notion of choice and the other by dynamic operators for belief change and desire change.
arXiv Detail & Related papers (2021-02-16T10:28:49Z) - Towards the Role of Theory of Mind in Explanation [23.818659473644505]
Theory of Mind is the ability to attribute mental states (e.g., beliefs, goals) to oneself, and to others.
Previous work has observed that Theory of Mind capabilities are central to providing an explanation to another agent.
arXiv Detail & Related papers (2020-05-06T17:13:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.