{"id":6851,"date":"2023-10-27T19:21:39","date_gmt":"2023-10-27T19:21:39","guid":{"rendered":"https:\/\/dailyai.com\/?p=6851"},"modified":"2023-10-27T22:55:24","modified_gmt":"2023-10-27T22:55:24","slug":"ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization","status":"publish","type":"post","link":"https:\/\/dailyai.com\/fr\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/","title":{"rendered":"L'IA soumise \u00e0 des tests sur la th\u00e9orie de l'esprit et la g\u00e9n\u00e9ralisation syst\u00e9matique"},"content":{"rendered":"

Des chercheurs ont pr\u00e9sent\u00e9 FANToM, un nouveau benchmark con\u00e7u pour tester et \u00e9valuer rigoureusement la compr\u00e9hension et l'application de la th\u00e9orie de l'esprit (ToM) par les grands mod\u00e8les de langage (LLM).<\/b><\/p>\n

La th\u00e9orie de l'esprit fait r\u00e9f\u00e9rence \u00e0 la capacit\u00e9 d'attribuer des croyances, des d\u00e9sirs et des connaissances \u00e0 soi-m\u00eame et aux autres, et de comprendre que les autres ont des croyances et des perspectives diff\u00e9rentes des siennes.\u00a0<\/span><\/p>\n

La ToM est consid\u00e9r\u00e9e comme un \u00e9l\u00e9ment fondamental de la conscience que poss\u00e8dent les animaux intelligents. Outre les humains, les primates tels que les orangs-outans, les gorilles et les chimpanz\u00e9s sont consid\u00e9r\u00e9s comme dot\u00e9s de la ToM, de m\u00eame que certains non-primates tels que les perroquets et les membres de la famille des corvid\u00e9s (corbeaux).\u00a0<\/span><\/p>\n

Les mod\u00e8les d'IA devenant de plus en plus complexes, les chercheurs en IA recherchent de nouvelles m\u00e9thodes d'\u00e9valuation des capacit\u00e9s telles que la ToM.<\/span><\/p>\n

Une nouvelle r\u00e9f\u00e9rence appel\u00e9e FANToM<\/span><\/a>cr\u00e9\u00e9 par des chercheurs de l'Allen Institute for AI, de l'universit\u00e9 de Washington, de l'universit\u00e9 Carnegie Mellon et de l'universit\u00e9 nationale de S\u00e9oul, soumet des mod\u00e8les d'apprentissage automatique \u00e0 des sc\u00e9narios dynamiques refl\u00e9tant les interactions de la vie r\u00e9elle.\u00a0<\/span><\/p>\n

Avec FANToM, les personnages entrent et sortent des conversations, ce qui met les mod\u00e8les d'IA au d\u00e9fi de maintenir une compr\u00e9hension pr\u00e9cise de qui sait quoi \u00e0 tout moment.<\/span><\/p>\n

L'utilisation de grands mod\u00e8les linguistiques (LLM) dans le cadre de FANToM a r\u00e9v\u00e9l\u00e9 que m\u00eame les mod\u00e8les les plus avanc\u00e9s ont du mal \u00e0 maintenir un ToM coh\u00e9rent.\u00a0<\/span><\/p>\n

Les performances des mod\u00e8les \u00e9taient nettement inf\u00e9rieures \u00e0 celles des participants humains, ce qui met en \u00e9vidence les limites de l'IA dans la compr\u00e9hension et la gestion d'interactions sociales complexes.\u00a0<\/span><\/p>\n

En fait, les humains ont domin\u00e9 toutes les cat\u00e9gories, comme le montre le tableau ci-dessous.\u00a0<\/span><\/p>\n

\"AI
Les humains ont \u00e9t\u00e9 bien meilleurs que les LLM populaires pour r\u00e9pondre aux questions li\u00e9es \u00e0 la ToM. Source : FANToM<\/a>.<\/figcaption><\/figure>\n

Il est int\u00e9ressant de noter que la version d'octobre du mod\u00e8le GPT-4 a \u00e9t\u00e9 surclass\u00e9e par une version ant\u00e9rieure de juin, ce qui pourrait confirmer les r\u00e9centes anecdotes des utilisateurs selon lesquelles le mod\u00e8le GPT-4 est plus performant que le mod\u00e8le GPT-4. <\/span>ChatGPT s'aggrave<\/span><\/a>.\u00a0<\/span><\/p>\n

FANToM a \u00e9galement r\u00e9v\u00e9l\u00e9 des techniques permettant d'am\u00e9liorer le ToM LLM, telles que le raisonnement par cha\u00eene de pens\u00e9e et d'autres m\u00e9thodes de mise au point. <\/span><\/p>\n

Toutefois, l'\u00e9cart entre les comp\u00e9tences de l'IA et celles des humains en mati\u00e8re de gestion des connaissances reste important.\u00a0<\/span><\/p>\n

L'IA progresse vers des comp\u00e9tences linguistiques comparables \u00e0 celles de l'homme<\/span><\/h2>\n

Dans un domaine quelque peu connexe mais distinct <\/span>publi\u00e9e dans Nature<\/span><\/a>Des scientifiques ont mis au point un r\u00e9seau neuronal capable de g\u00e9n\u00e9raliser le langage \u00e0 l'instar de l'homme.\u00a0<\/span><\/p>\n

Ce nouveau r\u00e9seau neuronal a fait preuve d'une capacit\u00e9 impressionnante \u00e0 int\u00e9grer des mots nouvellement appris dans son vocabulaire existant. Il pouvait ensuite utiliser ces mots dans diff\u00e9rents contextes, une comp\u00e9tence cognitive connue sous le nom de g\u00e9n\u00e9ralisation syst\u00e9matique.\u00a0<\/span><\/p>\n

Les \u00eatres humains font naturellement preuve d'une g\u00e9n\u00e9ralisation syst\u00e9matique, incorporant sans difficult\u00e9 un nouveau vocabulaire \u00e0 leur r\u00e9pertoire.\u00a0<\/span><\/p>\n

Par exemple, lorsque quelqu'un apprend le terme \"photobomb\", il peut l'appliquer \u00e0 diverses situations presque imm\u00e9diatement. De nouveaux termes d'argot apparaissent en permanence et les \u00eatres humains les int\u00e8grent naturellement \u00e0 leur vocabulaire.\u00a0<\/span><\/p>\n

Les chercheurs ont soumis leur propre r\u00e9seau neuronal et ChatGPT \u00e0 une s\u00e9rie de tests et ont constat\u00e9 que ChatGPT \u00e9tait moins performant que le mod\u00e8le personnalis\u00e9.<\/span><\/p>\n

Si les LLM tels que ChatGPT excellent dans de nombreux sc\u00e9narios de conversation, ils pr\u00e9sentent des incoh\u00e9rences et des lacunes notables dans d'autres, un probl\u00e8me auquel ce nouveau r\u00e9seau neuronal s'attaque.<\/span><\/p>\n

Pour \u00e9tudier cet aspect de la communication linguistique, des chercheurs ont men\u00e9 une exp\u00e9rience avec 25 participants humains, \u00e9valuant leur capacit\u00e9 \u00e0 appliquer des mots nouvellement appris dans diff\u00e9rents contextes. <\/span>Les sujets ont \u00e9t\u00e9 initi\u00e9s \u00e0 un pseudo-langage compos\u00e9 de mots absurdes repr\u00e9sentant diverses actions et r\u00e8gles.\u00a0<\/span><\/p>\n

Apr\u00e8s une phase d'entra\u00eenement, les participants ont excell\u00e9 dans l'application de ces r\u00e8gles abstraites \u00e0 de nouvelles situations, faisant preuve d'une g\u00e9n\u00e9ralisation syst\u00e9matique.<\/span><\/p>\n

Lorsque le r\u00e9seau neuronal nouvellement d\u00e9velopp\u00e9 a \u00e9t\u00e9 expos\u00e9 \u00e0 cette t\u00e2che, il a reproduit les performances humaines. <\/span>Cependant, lorsque ChatGPT a \u00e9t\u00e9 soumis au m\u00eame d\u00e9fi, il a \u00e9prouv\u00e9 des difficult\u00e9s consid\u00e9rables, \u00e9chouant entre 42 et 86% du temps, en fonction de la t\u00e2che sp\u00e9cifique.<\/span><\/p>\n

Ce r\u00e9sultat est significatif pour deux raisons. Tout d'abord, on peut affirmer que ce nouveau r\u00e9seau neuronal a effectivement surpass\u00e9 le GPT-4 dans cette t\u00e2che sp\u00e9cifique, ce qui est d\u00e9j\u00e0 impressionnant. Deuxi\u00e8mement, cette \u00e9tude pr\u00e9sente de nouvelles m\u00e9thodes pour enseigner aux mod\u00e8les d'IA comment g\u00e9n\u00e9raliser un nouveau langage comme les humains.\u00a0<\/span><\/p>\n

Comme l'explique Elia Bruni, sp\u00e9cialiste du traitement du langage naturel \u00e0 l'universit\u00e9 d'Osnabr\u00fcck, en Allemagne, \"l'introduction de la syst\u00e9maticit\u00e9 dans les r\u00e9seaux neuronaux est un enjeu de taille\".<\/span><\/p>\n

Ensemble, ces deux \u00e9tudes proposent de nouvelles approches pour former des mod\u00e8les d'IA plus intelligents, capables de rivaliser avec les humains dans des domaines essentiels tels que la linguistique et la th\u00e9orie de l'esprit. <\/span><\/p>","protected":false},"excerpt":{"rendered":"

Des chercheurs ont pr\u00e9sent\u00e9 FANToM, un nouveau benchmark con\u00e7u pour tester et \u00e9valuer rigoureusement la compr\u00e9hension et l'application de la th\u00e9orie de l'esprit (ToM) par les grands mod\u00e8les de langage (LLM). La th\u00e9orie de l'esprit fait r\u00e9f\u00e9rence \u00e0 la capacit\u00e9 d'attribuer des croyances, des d\u00e9sirs et des connaissances \u00e0 soi-m\u00eame et aux autres, et de comprendre que les autres ont des croyances et des perspectives diff\u00e9rentes des siennes. La th\u00e9orie de l'esprit est consid\u00e9r\u00e9e comme un \u00e9l\u00e9ment fondamental de la conscience que poss\u00e8dent les animaux intelligents. Outre les humains, les primates tels que les orangs-outans, les gorilles et les chimpanz\u00e9s sont consid\u00e9r\u00e9s comme dot\u00e9s de la ToM, de m\u00eame que certains non-primates tels que les perroquets et les membres de la famille des corvid\u00e9s (corbeaux). En tant que mod\u00e8les d'IA<\/p>","protected":false},"author":2,"featured_media":6853,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[404,115,105,93],"class_list":["post-6851","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-agi","tag-chatgpt","tag-machine-learning","tag-openai"],"yoast_head":"\nAI subjected to tests on Theory of Mind and systematic generalization | DailyAI<\/title>\n<meta name=\"description\" content=\"Researchers have introduced FANToM, a novel benchmark designed to rigorously test and evaluate large language models\u2019 (LLMs) understanding and application of Theory of Mind (ToM).\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/fr\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI subjected to tests on Theory of Mind and systematic generalization | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers have introduced FANToM, a novel benchmark designed to rigorously test and evaluate large language models\u2019 (LLMs) understanding and application of Theory of Mind (ToM).\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/fr\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-10-27T19:21:39+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-10-27T22:55:24+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_435449356.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"667\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Sam Jeans\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sam Jeans\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"AI subjected to tests on Theory of Mind and systematic generalization\",\"datePublished\":\"2023-10-27T19:21:39+00:00\",\"dateModified\":\"2023-10-27T22:55:24+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/\"},\"wordCount\":665,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/shutterstock_435449356.jpg\",\"keywords\":[\"AGI\",\"ChatGPT\",\"machine learning\",\"OpenAI\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"fr-FR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/\",\"name\":\"AI subjected to tests on Theory of Mind and systematic generalization | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/shutterstock_435449356.jpg\",\"datePublished\":\"2023-10-27T19:21:39+00:00\",\"dateModified\":\"2023-10-27T22:55:24+00:00\",\"description\":\"Researchers have introduced FANToM, a novel benchmark designed to rigorously test and evaluate large language models\u2019 (LLMs) understanding and application of Theory of Mind (ToM).\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/shutterstock_435449356.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/shutterstock_435449356.jpg\",\"width\":1000,\"height\":667,\"caption\":\"Theory of Mind AI\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AI subjected to tests on Theory of Mind and systematic generalization\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\",\"name\":\"Sam Jeans\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"caption\":\"Sam Jeans\"},\"description\":\"Sam is a science and technology writer who has worked in various AI startups. When he\u2019s not writing, he can be found reading medical journals or digging through boxes of vinyl records.\",\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/sam-jeans-6746b9142\\\/\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/fr\\\/author\\\/samjeans\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"L'IA est soumise \u00e0 des tests sur la th\u00e9orie de l'esprit et la g\u00e9n\u00e9ralisation syst\u00e9matique | DailyAI","description":"Des chercheurs ont pr\u00e9sent\u00e9 FANToM, un nouveau benchmark con\u00e7u pour tester et \u00e9valuer rigoureusement la compr\u00e9hension et l'application de la th\u00e9orie de l'esprit (ToM) par les grands mod\u00e8les de langage (LLM).","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/fr\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/","og_locale":"fr_FR","og_type":"article","og_title":"AI subjected to tests on Theory of Mind and systematic generalization | DailyAI","og_description":"Researchers have introduced FANToM, a novel benchmark designed to rigorously test and evaluate large language models\u2019 (LLMs) understanding and application of Theory of Mind (ToM).","og_url":"https:\/\/dailyai.com\/fr\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/","og_site_name":"DailyAI","article_published_time":"2023-10-27T19:21:39+00:00","article_modified_time":"2023-10-27T22:55:24+00:00","og_image":[{"width":1000,"height":667,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_435449356.jpg","type":"image\/jpeg"}],"author":"Sam Jeans","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"\u00c9crit par":"Sam Jeans","Dur\u00e9e de lecture estim\u00e9e":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"AI subjected to tests on Theory of Mind and systematic generalization","datePublished":"2023-10-27T19:21:39+00:00","dateModified":"2023-10-27T22:55:24+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/"},"wordCount":665,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_435449356.jpg","keywords":["AGI","ChatGPT","machine learning","OpenAI"],"articleSection":["Industry"],"inLanguage":"fr-FR"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/","url":"https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/","name":"L'IA est soumise \u00e0 des tests sur la th\u00e9orie de l'esprit et la g\u00e9n\u00e9ralisation syst\u00e9matique | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_435449356.jpg","datePublished":"2023-10-27T19:21:39+00:00","dateModified":"2023-10-27T22:55:24+00:00","description":"Des chercheurs ont pr\u00e9sent\u00e9 FANToM, un nouveau benchmark con\u00e7u pour tester et \u00e9valuer rigoureusement la compr\u00e9hension et l'application de la th\u00e9orie de l'esprit (ToM) par les grands mod\u00e8les de langage (LLM).","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_435449356.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_435449356.jpg","width":1000,"height":667,"caption":"Theory of Mind AI"},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/10\/ai-subjected-to-tests-on-theory-of-mind-and-systematic-generalization\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"AI subjected to tests on Theory of Mind and systematic generalization"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Votre dose quotidienne de nouvelles sur l'IA","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9","name":"Sam Jeans","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","caption":"Sam Jeans"},"description":"Sam est un r\u00e9dacteur scientifique et technologique qui a travaill\u00e9 dans diverses start-ups sp\u00e9cialis\u00e9es dans l'IA. Lorsqu'il n'\u00e9crit pas, on peut le trouver en train de lire des revues m\u00e9dicales ou de fouiller dans des bo\u00eetes de disques vinyles.","sameAs":["https:\/\/www.linkedin.com\/in\/sam-jeans-6746b9142\/"],"url":"https:\/\/dailyai.com\/fr\/author\/samjeans\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/6851","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/comments?post=6851"}],"version-history":[{"count":5,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/6851\/revisions"}],"predecessor-version":[{"id":6866,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/6851\/revisions\/6866"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media\/6853"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media?parent=6851"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/categories?post=6851"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/tags?post=6851"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}