{"id":11172,"date":"2024-04-02T09:32:07","date_gmt":"2024-04-02T09:32:07","guid":{"rendered":"https:\/\/dailyai.com\/?p=11172"},"modified":"2024-04-02T09:32:07","modified_gmt":"2024-04-02T09:32:07","slug":"deepmind-developed-safe-an-ai-agent-to-fact-check-llms","status":"publish","type":"post","link":"https:\/\/dailyai.com\/fr\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","title":{"rendered":"DeepMind a mis au point SAFE, un agent d'intelligence artificielle pour v\u00e9rifier les faits dans les manuels d'apprentissage tout au long de la vie."},"content":{"rendered":"

Des chercheurs de DeepMind et de l'universit\u00e9 de Stanford ont mis au point un agent d'IA qui v\u00e9rifie les faits et permet d'\u00e9valuer la factualit\u00e9 des mod\u00e8les d'IA.<\/strong><\/p>\n

M\u00eame les meilleurs mod\u00e8les d'IA ont encore tendance \u00e0 halluciner<\/a> parfois. Si vous demandez \u00e0 ChatGPT de vous donner les faits sur un sujet, plus sa r\u00e9ponse est longue, plus il est probable qu'elle contienne des faits qui ne sont pas vrais.<\/p>\n

Quels mod\u00e8les sont plus pr\u00e9cis que d'autres lorsqu'ils g\u00e9n\u00e8rent des r\u00e9ponses plus longues ? Il est difficile de le dire car, jusqu'\u00e0 pr\u00e9sent, nous ne disposions pas d'un point de r\u00e9f\u00e9rence pour mesurer l'exactitude des faits dans les r\u00e9ponses au formulaire long du programme LLM.<\/p>\n

DeepMind a d'abord utilis\u00e9 GPT-4 pour cr\u00e9er LongFact, un ensemble de 2 280 invites sous forme de questions li\u00e9es \u00e0 38 sujets. Ces invites suscitent des r\u00e9ponses longues de la part du LLM test\u00e9.<\/p>\n

Ils ont ensuite cr\u00e9\u00e9 un agent d'IA utilisant GPT-3.5-turbo pour utiliser Google afin de v\u00e9rifier si les r\u00e9ponses g\u00e9n\u00e9r\u00e9es par le LLM \u00e9taient factuelles. Ils ont appel\u00e9 cette m\u00e9thode Search-Augmented Factuality Evaluator (SAFE).<\/p>\n

SAFE d\u00e9compose d'abord la r\u00e9ponse longue du LLM en faits individuels. Il envoie ensuite des demandes de recherche \u00e0 Google Search et se prononce sur la v\u00e9racit\u00e9 du fait en se basant sur les informations contenues dans les r\u00e9sultats de la recherche.<\/p>\n

Voici un exemple tir\u00e9 de la document de recherche<\/a>.<\/p>\n

\"\"
Une invite \u00e0 la recherche de faits donne lieu \u00e0 une r\u00e9ponse longue. La r\u00e9ponse est d\u00e9compos\u00e9e en faits individuels, r\u00e9vis\u00e9e pour \u00eatre autonome, v\u00e9rifi\u00e9e pour la pertinence et v\u00e9rifi\u00e9e \u00e0 l'aide de Google Search. Source : arXiv<\/figcaption><\/figure>\n

Les chercheurs affirment que SAFE atteint des \"performances surhumaines\" par rapport aux annotateurs humains charg\u00e9s de la v\u00e9rification des faits.<\/p>\n

SAFE a approuv\u00e9 72% des annotations humaines et, en cas de divergence avec les humains, il s'est av\u00e9r\u00e9 juste dans 76% des cas. Il \u00e9tait \u00e9galement 20 fois moins cher que les annotateurs humains issus du crowdsourcing. Les LLM sont donc des v\u00e9rificateurs de faits meilleurs et moins chers que les humains.<\/p>\n

La qualit\u00e9 de la r\u00e9ponse des MFR test\u00e9s a \u00e9t\u00e9 mesur\u00e9e sur la base du nombre de facto\u00efdes dans la r\u00e9ponse et du degr\u00e9 d'exactitude des facto\u00efdes individuels.<\/p>\n

La mesure qu'ils ont utilis\u00e9e (F1@K) estime le nombre \"id\u00e9al\" de faits pr\u00e9f\u00e9r\u00e9s par l'homme dans une r\u00e9ponse. Les tests de r\u00e9f\u00e9rence ont utilis\u00e9 64 comme m\u00e9diane pour K et 178 comme maximum.<\/p>\n

En d'autres termes, F1@K est une mesure de \"La r\u00e9ponse m'a-t-elle donn\u00e9 autant de faits que je le souhaitais ?\" combin\u00e9e \u00e0 \"Combien de ces faits \u00e9taient vrais ?\".<\/p>\n

Quel est le LLM le plus factuel ?<\/h2>\n

Les chercheurs ont utilis\u00e9 LongFact pour demander \u00e0 13 LLM des familles Gemini, GPT, Claude et PaLM-2 de r\u00e9pondre. Ils ont ensuite utilis\u00e9 SAFE pour \u00e9valuer le caract\u00e8re factuel de leurs r\u00e9ponses.<\/p>\n

Le GPT-4-Turbo arrive en t\u00eate de liste des mod\u00e8les les plus factuels lorsqu'il s'agit de g\u00e9n\u00e9rer des r\u00e9ponses longues. Il est suivi de pr\u00e8s par Gemini-Ultra et PaLM-2-L-IT-RLHF. Les r\u00e9sultats montrent que les grands LLM sont plus factuels que les petits.<\/p>\n

Le calcul de F1@K passionnerait probablement les sp\u00e9cialistes des donn\u00e9es, mais, par souci de simplicit\u00e9, ces r\u00e9sultats de r\u00e9f\u00e9rence montrent \u00e0 quel point chaque mod\u00e8le est factuel lorsqu'il renvoie des r\u00e9ponses de longueur moyenne et des r\u00e9ponses plus longues aux questions.<\/p>\n

\"\"
Performance de factualit\u00e9 \u00e0 long terme de 13 LLM avec K = 64 (le nombre m\u00e9dian de faits parmi toutes les r\u00e9ponses du mod\u00e8le) et K = 178 (le nombre maximum de faits parmi toutes les r\u00e9ponses du mod\u00e8le). Source : arXiv<\/figcaption><\/figure>\n

SAFE est un moyen peu co\u00fbteux et efficace de quantifier la factualit\u00e9 des formulaires longs LLM. Il est plus rapide et moins co\u00fbteux que les humains pour la v\u00e9rification des faits, mais il d\u00e9pend toujours de la v\u00e9racit\u00e9 des informations que Google renvoie dans les r\u00e9sultats de recherche.<\/p>\n

DeepMind a mis SAFE \u00e0 la disposition du public et a sugg\u00e9r\u00e9 qu'il pourrait contribuer \u00e0 am\u00e9liorer la factualit\u00e9 des LLM par le biais d'une meilleure formation pr\u00e9alable et d'un r\u00e9glage fin. Il pourrait \u00e9galement permettre \u00e0 un LLM de v\u00e9rifier ses faits avant de pr\u00e9senter la sortie \u00e0 un utilisateur.<\/p>\n

L'OpenAI sera heureuse de constater que les recherches men\u00e9es par Google montrent que GPT-4 bat Gemini dans un autre test de r\u00e9f\u00e9rence.<\/p>","protected":false},"excerpt":{"rendered":"

Des chercheurs de DeepMind et de l'universit\u00e9 de Stanford ont mis au point un agent d'IA qui v\u00e9rifie les faits des LLM et permet d'\u00e9valuer la factualit\u00e9 des mod\u00e8les d'IA. M\u00eame les meilleurs mod\u00e8les d'IA ont parfois tendance \u00e0 halluciner. Si vous demandez \u00e0 ChatGPT de vous donner les faits sur un sujet, plus sa r\u00e9ponse est longue, plus il est probable qu'elle contienne des faits qui ne sont pas vrais. Quels mod\u00e8les sont plus pr\u00e9cis que d'autres lorsqu'ils g\u00e9n\u00e8rent des r\u00e9ponses plus longues ? Il est difficile de le dire car, jusqu'\u00e0 pr\u00e9sent, nous ne disposions pas d'un point de r\u00e9f\u00e9rence pour mesurer la factualit\u00e9 des r\u00e9ponses longues de LLM. DeepMind a d'abord utilis\u00e9 le GPT-4 pour cr\u00e9er LongFact, un ensemble de r\u00e9ponses \u00e0 un questionnaire.<\/p>","protected":false},"author":6,"featured_media":11182,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[147,118],"class_list":["post-11172","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-deepmind","tag-llms"],"yoast_head":"\nDeepMind developed SAFE, an AI agent to fact-check LLMs | DailyAI<\/title>\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\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"DeepMind developed SAFE, an AI agent to fact-check LLMs | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from DeepMind and Stanford University developed an AI agent that fact-checks LLMs and enables benchmarking of AI model factuality. Even the best AI models still tend to hallucinate at times. If you ask ChatGPT to give you the facts about a topic, the longer its response the more likely it is to include some facts that aren\u2019t true. Which models are more factually accurate than others when generating longer answers? It\u2019s hard to say because until now, we didn\u2019t have a benchmark measuring the factuality of LLM long-form responses. DeepMind first used GPT-4 to create LongFact, a set of\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/fr\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-02T09:32:07+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1792\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Eugene van der Watt\" \/>\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=\"Eugene van der Watt\" \/>\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\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"DeepMind developed SAFE, an AI agent to fact-check LLMs\",\"datePublished\":\"2024-04-02T09:32:07+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\"},\"wordCount\":611,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"keywords\":[\"DeepMind\",\"LLMS\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"fr-FR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\",\"name\":\"DeepMind developed SAFE, an AI agent to fact-check LLMs | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"datePublished\":\"2024-04-02T09:32:07+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/fact-vs-fake.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"DeepMind developed SAFE, an AI agent to fact-check LLMs\"}]},{\"@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\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"caption\":\"Eugene van der Watt\"},\"description\":\"Eugene comes from an electronic engineering background and loves all things tech. When he takes a break from consuming AI news you'll find him at the snooker table.\",\"sameAs\":[\"www.linkedin.com\\\/in\\\/eugene-van-der-watt-16828119\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/fr\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"DeepMind a d\u00e9velopp\u00e9 SAFE, un agent d'IA pour v\u00e9rifier les faits des LLMs | DailyAI","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\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","og_locale":"fr_FR","og_type":"article","og_title":"DeepMind developed SAFE, an AI agent to fact-check LLMs | DailyAI","og_description":"Researchers from DeepMind and Stanford University developed an AI agent that fact-checks LLMs and enables benchmarking of AI model factuality. Even the best AI models still tend to hallucinate at times. If you ask ChatGPT to give you the facts about a topic, the longer its response the more likely it is to include some facts that aren\u2019t true. Which models are more factually accurate than others when generating longer answers? It\u2019s hard to say because until now, we didn\u2019t have a benchmark measuring the factuality of LLM long-form responses. DeepMind first used GPT-4 to create LongFact, a set of","og_url":"https:\/\/dailyai.com\/fr\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","og_site_name":"DailyAI","article_published_time":"2024-04-02T09:32:07+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","type":"image\/webp"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"\u00c9crit par":"Eugene van der Watt","Dur\u00e9e de lecture estim\u00e9e":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"DeepMind developed SAFE, an AI agent to fact-check LLMs","datePublished":"2024-04-02T09:32:07+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/"},"wordCount":611,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","keywords":["DeepMind","LLMS"],"articleSection":["Industry"],"inLanguage":"fr-FR"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","url":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/","name":"DeepMind a d\u00e9velopp\u00e9 SAFE, un agent d'IA pour v\u00e9rifier les faits des LLMs | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","datePublished":"2024-04-02T09:32:07+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/fact-vs-fake.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-developed-safe-an-ai-agent-to-fact-check-llms\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"DeepMind developed SAFE, an AI agent to fact-check LLMs"}]},{"@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\/7ce525c6d0c79838b7cc7cde96993cfa","name":"Eug\u00e8ne van der Watt","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","caption":"Eugene van der Watt"},"description":"Eugene a une formation d'ing\u00e9nieur en \u00e9lectronique et adore tout ce qui touche \u00e0 la technologie. Lorsqu'il fait une pause dans sa consommation d'informations sur l'IA, vous le trouverez \u00e0 la table de snooker.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/fr\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/11172","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\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/comments?post=11172"}],"version-history":[{"count":2,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/11172\/revisions"}],"predecessor-version":[{"id":11181,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/11172\/revisions\/11181"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media\/11182"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media?parent=11172"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/categories?post=11172"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/tags?post=11172"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}