{"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/evaluating-theory-of-mind-in-question","title":"Evaluating Theory of Mind in Question Answering","arxiv_id":"1808.09352","date":"2018-08-28","proceeding":"EMNLP 2018 10","authors":["Aida Nematzadeh","Kaylee Burns","Erin Grant","Alison Gopnik","Thomas L. Griffiths"],"abstract":"We propose a new dataset for evaluating question answering models with\nrespect to their capacity to reason about beliefs. Our tasks are inspired by\ntheory-of-mind experiments that examine whether children are able to reason\nabout the beliefs of others, in particular when those beliefs differ from\nreality. We evaluate a number of recent neural models with memory augmentation.\nWe find that all fail on our tasks, which require keeping track of inconsistent\nstates of the world; moreover, the models' accuracy decreases notably when\nrandom sentences are introduced to the tasks at test.","url_abs":"http://arxiv.org/abs/1808.09352v1","url_pdf":"http://arxiv.org/pdf/1808.09352v1.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":"evaluating-theory-of-mind-in-question","repo_url":"https://github.com/kayburns/tom-qa-dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"evaluating-theory-of-mind-in-question","repo_url":"https://github.com/GoodAI/goodai-ltm-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"evaluating-theory-of-mind-in-question","repo_url":"https://github.com/facebookresearch/tomi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[{"slug":"tom-qa","name":"ToM QA","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.09352","atlas_url":"https://app.syntology.ai/?focus=1808.09352","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}