{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/solving-the-baby-intuitions-benchmark-with-a","title":"Solving the Baby Intuitions Benchmark with a Hierarchically Bayesian Theory of Mind","arxiv_id":"2208.02914","date":"2022-08-04","proceeding":null,"authors":["Tan Zhi-Xuan","Nishad Gothoskar","Falk Pollok","Dan Gutfreund","Joshua B. Tenenbaum","Vikash K. Mansinghka"],"abstract":"To facilitate the development of new models to bridge the gap between machine and human social intelligence, the recently proposed Baby Intuitions Benchmark (arXiv:2102.11938) provides a suite of tasks designed to evaluate commonsense reasoning about agents' goals and actions that even young infants exhibit. Here we present a principled Bayesian solution to this benchmark, based on a hierarchically Bayesian Theory of Mind (HBToM). By including hierarchical priors on agent goals and dispositions, inference over our HBToM model enables few-shot learning of the efficiency and preferences of an agent, which can then be used in commonsense plausibility judgements about subsequent agent behavior. This approach achieves near-perfect accuracy on most benchmark tasks, outperforming deep learning and imitation learning baselines while producing interpretable human-like inferences, demonstrating the advantages of structured Bayesian models of human social cognition.","url_abs":"https://arxiv.org/abs/2208.02914v1","url_pdf":"https://arxiv.org/pdf/2208.02914v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"solving-the-baby-intuitions-benchmark-with-a","repo_url":"https://github.com/probcomp/solvingbib.jl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2208.02914","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}