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
- 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) - MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation [62.44907105496227]
MindDial is a novel conversational framework that can generate situated free-form responses with theory-of-mind modeling.
We introduce an explicit mind module that can track the speaker's belief and the speaker's prediction of the listener's belief.
Our framework is applied to both prompting and fine-tuning-based models, and is evaluated across scenarios involving both common ground alignment and negotiation.
arXiv Detail & Related papers (2023-06-27T07:24:32Z) - 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) - On the Computation of Meaning, Language Models and Incomprehensible Horrors [0.0]
We integrate foundational theories of meaning with a mathematical formalism of artificial general intelligence (AGI)
Our findings shed light on the relationship between meaning and intelligence, and how we can build machines that comprehend and intend meaning.
arXiv Detail & Related papers (2023-04-25T09:41:00Z) - 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) - Cognitive Argumentation and the Suppression Task [1.027974860479791]
This paper addresses the challenge of modeling human reasoning, within a new framework called Cognitive Argumentation.
The framework relies on cognitive principles, based on empirical and theoretical work in Cognitive Science, to adapt a general and abstract framework of computational argumentation from AI.
We argue that Cognitive Argumentation provides a coherent and cognitively adequate model for human conditional reasoning.
arXiv Detail & Related papers (2020-02-24T10:30:39Z)
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.