arXiv cs.AI· Jeffrey Qin, Zhuangfei Gao, Wasu Top Piriyakulkij, Mia Radovanovic, Jessica Sommerville, Kevin Ellis, Marta Kryven·· 14 小时前AI 评分22
从不可靠证据中学习心智模型：基于贝叶斯粒子推理与 LLM 程序合成的儿童推断计算分析
Learning Mental Models From Unreliable Evidence
AI 导读
研究用贝叶斯粒子推理框架对儿童在 Box Task 中的推断行为做计算建模，模型需同时考虑证据的主观可靠性与在线假设生成，才能解释儿童行为的关键特征。假设以约束和可执行程序两种形式表示，程序化假设用 LLM 程序合成实现，在三种提示词变体和多个 LLM 后端上验证了稳健性。
正文 · 原文
Abstract:Children expertly construct mental models under uncertainty despite limited world knowledge. Which computational principles make this possible? We study this question in an interactive physical Box Task in which participants infer a latent cause through interaction with a stochastic and partially observed environment. The Box Task was originally designed to study children's puzzle-solving qualitatively. We contribute a computational analysis of behavior that formalizes the cognitive process by which children generate new hypotheses and respond to environmental uncertainty as inference unfolds. Our modeling framework is based on Bayesian particle-based inference, which maintains a small set of working hypotheses and continually generates new ones. We give two complementary implementations of hypothesis representations within this framework: (1) as constraints on evidence, and (2) as executable programs evaluated against evidence. Using the constraint-based formulation, we show that the model needs to account both for subjective reliability of evidence and online hypothesis generation to explain key signatures of children's behavior. Using the programmatic formulation, we show that hypotheses may take the form of partial compositional rules to guide information gathering when evidence interpretation is hard. The programmatic hypotheses are implemented using LLM-based program synthesis, evaluated across three prompt variants and several LLM backends, demonstrating robustness of our approach. Together, these results extend current models of children's inference to account for subjective reliability of evidence and open-ended hypothesis spaces, and provide a computational analysis of the form generated hypotheses may take in practice.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.24528 [cs.AI] |
| (or arXiv:2605.24528v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.24528 arXiv-issued DOI via DataCite |
Submission history
From: Marta Kryven [view email]
[v1]
Sat, 23 May 2026 11:38:56 UTC (2,979 KB)
[v2]
Sat, 30 May 2026 22:18:51 UTC (2,979 KB)
[v3]
Thu, 29 Oct 2026 14:17:54 UTC (3,212 KB)
来源：arXiv cs.AI · arxiv.org