{"id":10866,"date":"2024-03-22T10:03:11","date_gmt":"2024-03-22T10:03:11","guid":{"rendered":"https:\/\/dailyai.com\/?p=10866"},"modified":"2024-03-28T09:32:30","modified_gmt":"2024-03-28T09:32:30","slug":"quiet-star-teaches-language-models-to-think-before-they-speak","status":"publish","type":"post","link":"https:\/\/dailyai.com\/nb\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","title":{"rendered":"Quiet-STaR l\u00e6rer spr\u00e5kmodeller \u00e5 tenke f\u00f8r de snakker"},"content":{"rendered":"<p><strong>Forskere fra Stanford University og Notbad AI har utviklet Quiet-STaR, en teknikk som trener en spr\u00e5kmodell (LM) til \u00e5 resonnere internt f\u00f8r den genererer en utdata.<\/strong><\/p>\n<p>N\u00e5r vi mennesker snakker, har vi vanligvis en indre dialog som former ordene vi til slutt ytrer. Jo mer vi tenker f\u00f8r vi snakker, desto bedre blir kvaliteten p\u00e5 det vi sier.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/pdf\/2403.09629.pdf\" target=\"_blank\" rel=\"noopener\">I deres artikkel<\/a>beskriver forskerne hvordan de trente opp en LM (<a href=\"https:\/\/dailyai.com\/nb\/2024\/02\/mistral-ai-releases-new-model-and-chatbot-to-take-on-gpt-4\/\">Mistral-7B<\/a>) for \u00e5 l\u00e6re \u00e5 imitere denne prosessen p\u00e5 en generalisert m\u00e5te. Quiet-STaR er en videreutvikling av en annen teknikk som kalles STaR, eller Self-Taught Reasoner.<\/p>\n<p>STaR er en metode for \u00e5 trene opp en modell med noen f\u00e5 eksempler p\u00e5 sp\u00f8rsm\u00e5l med forklaringer (rasjonaler) for svarene. Modellen bruker disse tankekjedeeksemplene til \u00e5 pr\u00f8ve \u00e5 svare p\u00e5 sp\u00f8rsm\u00e5l p\u00e5 egen h\u00e5nd, og finner selv ut av begrunnelsene.<\/p>\n<p>STaR evaluerer om begrunnelsene den kommer frem til, resulterer i riktige svar eller ikke, og forbedrer begrunnelsene sine.<\/p>\n<p>Selv om STaR er imponerende, er dens evne til \u00e5 resonnere begrenset til sp\u00f8rsm\u00e5l-svar-sammenhenger (QA) under oppl\u00e6ringen. M\u00e5let med Quiet-STaR er \u00e5 gi LM en generalisert evne til \u00e5 l\u00e6re seg \u00e5 resonnere eller utvikle begrunnelser i et bredere spekter av tekster, ikke bare QA-datasett.<\/p>\n<h2>Hvordan fungerer Quiet-STaR?<\/h2>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">Spr\u00e5kmodeller er i dag oppl\u00e6rt til \u00e5 resonnere enten 1) generelt, ved \u00e5 imitere online resonneringsdata, eller 2) snevert, ved \u00e5 l\u00e6re seg sine egne l\u00f8sninger p\u00e5 spesifikke oppgaver<\/p>\n<p>Kan LM-er l\u00e6re seg selv \u00e5 resonnere generelt?\ud83c\udf1fInnf\u00f8ring av Quiet-STaR, selvl\u00e6ring via indre monolog!\ud83e\uddf5 <a href=\"https:\/\/t.co\/WCSxLPZeCX\">pic.twitter.com\/WCSxLPZeCX<\/a><\/p>\n<p>- Eric Zelikman (@ericzelikman) <a href=\"https:\/\/twitter.com\/ericzelikman\/status\/1768663835106513041?ref_src=twsrc%5Etfw\">15. mars 2024<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>En av de viktigste nyvinningene i Quiet-STaR er at den genererer rasjonaler, eller tanker, parallelt, etter alle tokens i teksten den behandler. Den skriver ikke ut disse tankekjedene, derav \"Quiet\"-delen av algoritmens navn.<\/p>\n<p>Algoritmen behandler begrunnelsene gjennom et \"blandingshode\". Hver begrunnelse evalueres basert p\u00e5 n\u00f8yaktigheten i prediksjonen av neste-token sammenlignet med prediksjonen fra basismodellen.<\/p>\n<p>Hvis basismodellen (uten Quiet-STaR) gir en bedre prediksjon, var ikke begrunnelsen god nok. Hvis begrunnelsen resulterer i en mer n\u00f8yaktig prediksjon av neste token, vet algoritmen at den er p\u00e5 sporet av noe bra.<\/p>\n<p>Deretter bruker den en forsterkende l\u00e6ringsalgoritme (REINFORCE) for \u00e5 l\u00e6re hvilke begrunnelser som hjelper og hvilke som hindrer modellens ytelse. Resultatet er at modellen l\u00e6rer seg en generalisert evne til \u00e5 tenke f\u00f8r den forutsier neste token.<\/p>\n<h2>Resultater fra Quiet-STaR<\/h2>\n<p>Forskerne testet den Quiet-STaR-trente Mistral-7B-modellen p\u00e5 GSM8K-matematikk- og CommonsenseQA-benchmarks for sunn fornuft. De fant ut at Quiet-STaR forbedret evnen til \u00e5 resonnere direkte og uten nullskudd p\u00e5 b\u00e5de CommonsenseQA (36,3% til 47,2%) og GSM8K (5,9% til 10,9%).<\/p>\n<figure id=\"attachment_10868\" aria-describedby=\"caption-attachment-10868\" style=\"width: 1334px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-10868\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results.jpg\" alt=\"\" width=\"1334\" height=\"518\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results.jpg 1334w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-300x116.jpg 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-1024x398.jpg 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-768x298.jpg 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-370x144.jpg 370w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-800x311.jpg 800w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-740x287.jpg 740w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-20x8.jpg 20w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-124x48.jpg 124w\" sizes=\"auto, (max-width: 1334px) 100vw, 1334px\" \/><figcaption id=\"caption-attachment-10868\" class=\"wp-caption-text\">Quiet-STaRs resultater p\u00e5 GMSK8-matematikk for barneskolen og CommonsenseQA-referanser for sunn fornuft. Hver linje representerer en iterasjon av Quiet-STaR med varierende lengde p\u00e5 tanketoken, og hvor mange tokens den resonnerte seg frem til. Basislinjen er Mistral-7B uten Quiet-STaR. Kilde: arXiv<\/figcaption><\/figure>\n<p>Selv om Mistral-7Bs matematiske resonnement fortsatt ikke er fantastisk, leverte Quiet-STaR en forbedring p\u00e5 nesten 85% i forhold til basismodellen, og dette var uten noen datasettspesifikk finjustering.\"<\/p>\n<p>Testresultatene viste ogs\u00e5 at prestasjonsforbedringene var direkte knyttet til hvor mange tokens som ble tildelt modellens indre tanker. Jo mer den tenkte f\u00f8r den svarte, desto bedre ble svaret.<\/p>\n<p>Disse forbedringene kommer p\u00e5 bekostning av et betydelig databehandlingsomfang. Den indre monologen som modellen f\u00f8rer under tankeprosessen, genererer mange tokens.<\/p>\n<p>Forbedringer i maskinvaren vil etter hvert gj\u00f8re det ekstra overheadet som f\u00f8lger med slike teknikker, mindre betydningsfullt.<\/p>\n<p>Forskerne konkluderer med at fremtidig arbeid med \u00e5 optimalisere Quiet-STaR ogs\u00e5 kan v\u00e6re til hjelp. Dynamisk forutsigelse av om en tankeprosess er n\u00f8dvendig, eller hvor lang den b\u00f8r v\u00e6re, kan redusere antall un\u00f8dvendige tankesekvenser.<\/p>\n<p>Resultatene fra trening av en liten modell som Mistral-7B med Quiet-STaR er lovende. Forskerne mener at \"de samme teknikkene anvendt p\u00e5 en bedre modell sannsynligvis vil gi uforholdsmessig mye bedre resultater\".<\/p>\n<h2>Etiske sp\u00f8rsm\u00e5l<\/h2>\n<p>\u00c5 f\u00e5 en spr\u00e5kmodell til \u00e5 resonnere mer som et menneske er forbundet med noen interessante problemstillinger og etiske sp\u00f8rsm\u00e5l.<\/p>\n<p>Forskerne p\u00e5peker at \"det er umulig \u00e5 vite at resonnementene som modellen uttrykker i spr\u00e5ket, representerer modellens interne prosessering p\u00e5 en n\u00f8yaktig m\u00e5te\". Begrunnelsene som modellen genererer, er naturlige spr\u00e5klige representasjoner av dens indre resonnementer. Er de en n\u00f8yaktig gjenspeiling?<\/p>\n<p>De bemerker videre at \"det finnes ingen garantier mot skadelige eller skjeve resonneringsm\u00f8nstre hvis modellen finner dem nyttige\".<\/p>\n<p>Vi kan v\u00e6re forn\u00f8yde med svaret fra en AI-modell, men det er ikke sikkert vi liker, eller forst\u00e5r, tankeprosessen som f\u00f8rte til det.<\/p>\n<p>En av artikkelens hovedforfattere, Eric Zelikman, ble nettopp ansatt i Elon Musks xAI denne uken. Han vil kanskje finne ut at <a href=\"https:\/\/dailyai.com\/nb\/2024\/03\/elon-musks-xai-open-sources-its-llm-grok-1\/\">Grok<\/a> er mindre opptatt av disse etiske sp\u00f8rsm\u00e5lene og mer begeistret over utsiktene til AI-utviklingen.<\/p>\n<p>&nbsp;<\/p>","protected":false},"excerpt":{"rendered":"<p>Forskere fra Stanford University og Notbad AI har utviklet Quiet-STaR, en teknikk som trener en spr\u00e5kmodell (LM) til \u00e5 resonnere internt f\u00f8r den genererer et resultat. N\u00e5r vi mennesker snakker, har vi normalt en indre dialog som former ordene vi til slutt ytrer. Jo mer vi tenker f\u00f8r vi snakker, desto bedre blir kvaliteten p\u00e5 det vi sier. I artikkelen beskriver forskerne hvordan de har trent opp en LM (Mistral-7B) til \u00e5 l\u00e6re seg \u00e5 imitere denne prosessen p\u00e5 en generalisert m\u00e5te. Quiet-STaR er en videreutvikling av en annen teknikk som kalles STaR, eller Self-Taught Reasoner. STaR er en metode for \u00e5 trene opp en modell med noen f\u00e5<\/p>","protected":false},"author":6,"featured_media":10869,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[118],"class_list":["post-10866","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-llms"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Quiet-STaR teaches language models to think before they speak | 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\/nb\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/\" \/>\n<meta property=\"og:locale\" content=\"nb_NO\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Quiet-STaR teaches language models to think before they speak | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from Stanford University and Notbad AI developed Quiet-STaR, a technique that trains a language model (LM) to reason internally before generating an output. When humans speak, we normally have an inner dialogue that shapes the words we eventually verbalize. The more we think before speaking, the better the quality of our spoken words. In their paper, the researchers describe how they trained an LM (Mistral-7B) to learn how to imitate this process in a generalized way. Quiet-STaR is a progression of another technique called STaR, or Self-Taught Reasoner. STaR is a method of training a model with a few\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/nb\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-03-22T10:03:11+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-03-28T09:32:30+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.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=\"Skrevet av\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Ansl. lesetid\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Quiet-STaR teaches language models to think before they speak\",\"datePublished\":\"2024-03-22T10:03:11+00:00\",\"dateModified\":\"2024-03-28T09:32:30+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/\"},\"wordCount\":808,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/the-thinker.webp\",\"keywords\":[\"LLMS\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"nb-NO\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/\",\"name\":\"Quiet-STaR teaches language models to think before they speak | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/the-thinker.webp\",\"datePublished\":\"2024-03-22T10:03:11+00:00\",\"dateModified\":\"2024-03-28T09:32:30+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#breadcrumb\"},\"inLanguage\":\"nb-NO\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"nb-NO\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/the-thinker.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/the-thinker.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Quiet-STaR teaches language models to think before they speak\"}]},{\"@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\":\"nb-NO\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"nb-NO\",\"@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\":\"nb-NO\",\"@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\\\/nb\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Quiet-STaR l\u00e6rer spr\u00e5kmodeller \u00e5 tenke f\u00f8r de snakker | 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\/nb\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","og_locale":"nb_NO","og_type":"article","og_title":"Quiet-STaR teaches language models to think before they speak | DailyAI","og_description":"Researchers from Stanford University and Notbad AI developed Quiet-STaR, a technique that trains a language model (LM) to reason internally before generating an output. When humans speak, we normally have an inner dialogue that shapes the words we eventually verbalize. The more we think before speaking, the better the quality of our spoken words. In their paper, the researchers describe how they trained an LM (Mistral-7B) to learn how to imitate this process in a generalized way. Quiet-STaR is a progression of another technique called STaR, or Self-Taught Reasoner. STaR is a method of training a model with a few","og_url":"https:\/\/dailyai.com\/nb\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","og_site_name":"DailyAI","article_published_time":"2024-03-22T10:03:11+00:00","article_modified_time":"2024-03-28T09:32:30+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.webp","type":"image\/webp"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Skrevet av":"Eugene van der Watt","Ansl. lesetid":"4 minutter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Quiet-STaR teaches language models to think before they speak","datePublished":"2024-03-22T10:03:11+00:00","dateModified":"2024-03-28T09:32:30+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/"},"wordCount":808,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.webp","keywords":["LLMS"],"articleSection":["Industry"],"inLanguage":"nb-NO"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","url":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","name":"Quiet-STaR l\u00e6rer spr\u00e5kmodeller \u00e5 tenke f\u00f8r de snakker | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.webp","datePublished":"2024-03-22T10:03:11+00:00","dateModified":"2024-03-28T09:32:30+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#breadcrumb"},"inLanguage":"nb-NO","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/"]}]},{"@type":"ImageObject","inLanguage":"nb-NO","@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Quiet-STaR teaches language models to think before they speak"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DagligAI","description":"Din daglige dose med AI-nyheter","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":"nb-NO"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DagligAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"nb-NO","@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":"nb-NO","@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 har bakgrunn som elektroingeni\u00f8r og elsker alt som har med teknologi \u00e5 gj\u00f8re. N\u00e5r han tar en pause fra AI-nyhetene, finner du ham ved snookerbordet.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/nb\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts\/10866","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/comments?post=10866"}],"version-history":[{"count":5,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts\/10866\/revisions"}],"predecessor-version":[{"id":10873,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/posts\/10866\/revisions\/10873"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/media\/10869"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/media?parent=10866"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/categories?post=10866"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/nb\/wp-json\/wp\/v2\/tags?post=10866"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}