{"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\/es\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","title":{"rendered":"Quiet-STaR ense\u00f1a a los modelos ling\u00fc\u00edsticos a pensar antes de hablar"},"content":{"rendered":"<p><strong>Investigadores de la Universidad de Stanford y Notbad AI desarrollaron Quiet-STaR, una t\u00e9cnica que entrena un modelo ling\u00fc\u00edstico (LM) para razonar internamente antes de generar una salida.<\/strong><\/p>\n<p>Cuando los seres humanos hablamos, normalmente mantenemos un di\u00e1logo interior que da forma a las palabras que finalmente verbalizamos. Cuanto m\u00e1s pensemos antes de hablar, mejor ser\u00e1 la calidad de nuestras palabras.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/pdf\/2403.09629.pdf\" target=\"_blank\" rel=\"noopener\">En su documento<\/a>los investigadores describen c\u00f3mo entrenaron un LM (<a href=\"https:\/\/dailyai.com\/es\/2024\/02\/mistral-ai-releases-new-model-and-chatbot-to-take-on-gpt-4\/\">Mistral-7B<\/a>) para aprender a imitar este proceso de forma generalizada. Quiet-STaR es una progresi\u00f3n de otra t\u00e9cnica llamada STaR, o Razonador Autodidacta.<\/p>\n<p>STaR es un m\u00e9todo de entrenamiento de un modelo con algunos ejemplos de preguntas con explicaciones (razonamientos) para las respuestas. El modelo utiliza estos ejemplos de cadena de pensamiento para intentar responder a las preguntas por s\u00ed mismo, descubriendo los razonamientos por s\u00ed mismo.<\/p>\n<p>STaR eval\u00faa si los razonamientos que elabora dan lugar a respuestas correctas y perfecciona sus razonamientos.<\/p>\n<p>A pesar de lo impresionante que es STaR, su capacidad de razonamiento se limita a los contextos de pregunta-respuesta (QA) durante el entrenamiento. El objetivo de Quiet-STaR es dotar a un LM de una capacidad generalizada para aprender a razonar o desarrollar razonamientos, a trav\u00e9s de una gama m\u00e1s amplia de textos, no s\u00f3lo de conjuntos de datos QA.<\/p>\n<h2>\u00bfC\u00f3mo funciona Quiet-STaR?<\/h2>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">Hoy en d\u00eda, los modelos ling\u00fc\u00edsticos se entrenan para razonar: 1) de forma general, imitando los datos de razonamiento en l\u00ednea, o 2) de forma restringida, aprendiendo por s\u00ed mismos a resolver tareas espec\u00edficas.<\/p>\n<p>\u00bfPueden los LM ense\u00f1arse a s\u00ed mismos a razonar en general?\ud83c\udf1fIntroducci\u00f3n de Quiet-STaR, \u00a1autoense\u00f1anza a trav\u00e9s del mon\u00f3logo interno!\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 de marzo de 2024<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>Una de las principales innovaciones de Quiet-STaR es que genera razonamientos, o pensamientos, en paralelo, siguiendo todos los tokens del texto que est\u00e1 procesando. No emite estos razonamientos en cadena, de ah\u00ed la parte \"silenciosa\" del nombre del algoritmo.<\/p>\n<p>El algoritmo procesa los razonamientos a trav\u00e9s de una \"cabeza mezcladora\". Cada razonamiento se eval\u00faa en funci\u00f3n de la precisi\u00f3n de la predicci\u00f3n del siguiente token que ha producido en comparaci\u00f3n con la predicci\u00f3n realizada por el modelo base.<\/p>\n<p>Si el modelo base (sin Quiet-STaR) ofrece una predicci\u00f3n mejor, entonces el razonamiento no era bueno. Si el razonamiento resulta en una predicci\u00f3n m\u00e1s precisa del siguiente token, entonces el algoritmo sabe que est\u00e1 haciendo algo bueno.<\/p>\n<p>A continuaci\u00f3n, utiliza un algoritmo de aprendizaje por refuerzo (REINFORCE) para aprender qu\u00e9 razonamientos ayudan y cu\u00e1les entorpecen el rendimiento del modelo. El resultado es que el modelo aprende una capacidad generalizada para pensar antes de predecir la siguiente ficha.<\/p>\n<h2>Resultados de Quiet-STaR<\/h2>\n<p>Los investigadores probaron el modelo Mistral-7B entrenado con Quiet-STaR en las pruebas de matem\u00e1ticas GSM8K y de razonamiento de sentido com\u00fan CommonsenseQA. Comprobaron que Quiet-STaR mejoraba la perplejidad y la capacidad de razonamiento directo sin disparo tanto en CommonsenseQA (de 36,3% a 47,2%) como en GSM8K (de 5,9% a 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\">Resultados de Quiet-STaR en las pruebas de matem\u00e1ticas de primaria GMSK8 y de razonamiento de sentido com\u00fan CommonsenseQA. Cada l\u00ednea representa una iteraci\u00f3n de Quiet-STaR con diferentes longitudes de tokens de pensamiento y cu\u00e1ntos tokens razon\u00f3 por adelantado. La referencia es Mistral-7B sin Quiet-STaR. Fuente: arXiv<\/figcaption><\/figure>\n<p>Aunque el razonamiento matem\u00e1tico de Mistral-7B sigue sin ser excelente, Quiet-STaR consigui\u00f3 una mejora de casi 85% sobre el modelo base, y esto sin ning\u00fan ajuste fino espec\u00edfico del conjunto de datos.\"<\/p>\n<p>Los resultados de las pruebas tambi\u00e9n mostraron que las mejoras en el rendimiento estaban directamente relacionadas con cu\u00e1ntos tokens se asignaban a los pensamientos internos del modelo. Cuanto m\u00e1s pensaba antes de responder, mejor era la respuesta.<\/p>\n<p>Estas mejoras se producen a costa de una considerable sobrecarga inform\u00e1tica. El mon\u00f3logo interior del modelo durante el proceso de pensamiento genera muchas fichas.<\/p>\n<p>Con el tiempo, las mejoras en el hardware har\u00e1n que la sobrecarga adicional que conllevan este tipo de t\u00e9cnicas sea menos importante.<\/p>\n<p>Los investigadores concluyen que el trabajo futuro para optimizar Quiet-STaR tambi\u00e9n podr\u00eda ayudar. Predecir din\u00e1micamente si se requiere un proceso de pensamiento, o cu\u00e1nto debe durar, podr\u00eda reducir los tokens de pensamiento innecesarios.<\/p>\n<p>Los resultados del entrenamiento de un modelo peque\u00f1o como Mistral-7B con Quiet-STaR son prometedores. Los investigadores creen que \"las mismas t\u00e9cnicas aplicadas a un modelo mejor probablemente dar\u00edan resultados desproporcionadamente mejores.\"<\/p>\n<h2>Cuestiones \u00e9ticas<\/h2>\n<p>Hacer que un modelo ling\u00fc\u00edstico razone m\u00e1s como un ser humano plantea algunos problemas interesantes y cuestiones \u00e9ticas.<\/p>\n<p>Los investigadores se\u00f1alan que \"es imposible saber si el razonamiento expresado por el modelo en el lenguaje representa con exactitud el procesamiento interno del modelo\". Los razonamientos que genera el modelo son representaciones en lenguaje natural de su razonamiento interno. \u00bfSon un reflejo exacto?<\/p>\n<p>Adem\u00e1s, se\u00f1alan que \"no hay salvaguardas contra patrones de razonamiento perjudiciales o sesgados si el modelo los considera \u00fatiles\".<\/p>\n<p>Puede que estemos satisfechos con la respuesta de un modelo de IA, pero puede que no nos guste, o incluso que no entendamos, el proceso de pensamiento que la ha dado.<\/p>\n<p>Uno de los autores principales del art\u00edculo, Eric Zelikman, acaba de incorporarse esta semana a la xAI de Elon Musk. \u00c9l puede encontrar que <a href=\"https:\/\/dailyai.com\/es\/2024\/03\/elon-musks-xai-open-sources-its-llm-grok-1\/\">Grok<\/a> est\u00e1 menos preocupado por estas cuestiones \u00e9ticas y m\u00e1s entusiasmado con la perspectiva del avance de la IA.<\/p>\n<p>&nbsp;<\/p>","protected":false},"excerpt":{"rendered":"<p>Investigadores de la Universidad de Stanford y Notbad AI han desarrollado Quiet-STaR, una t\u00e9cnica que entrena un modelo ling\u00fc\u00edstico (LM) para que razone internamente antes de generar un resultado. Cuando los humanos hablamos, normalmente mantenemos un di\u00e1logo interno que da forma a las palabras que finalmente verbalizamos. Cuanto m\u00e1s pensemos antes de hablar, mejor ser\u00e1 la calidad de nuestras palabras. En su art\u00edculo, los investigadores describen c\u00f3mo entrenaron a un LM (Mistral-7B) para que aprendiera a imitar este proceso de forma generalizada. Quiet-STaR es una evoluci\u00f3n de otra t\u00e9cnica llamada STaR, o razonador autodidacta. STaR es un m\u00e9todo de entrenamiento de un modelo con unos pocos<\/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\/es\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/\" \/>\n<meta property=\"og:locale\" content=\"es_ES\" \/>\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\/es\/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=\"Escrito por\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tiempo de lectura\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutos\" \/>\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\":\"es\"},{\"@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\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@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\":\"es\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@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\":\"es\",\"@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\\\/es\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Quiet-STaR ense\u00f1a a los modelos ling\u00fc\u00edsticos a pensar antes de hablar | 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\/es\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","og_locale":"es_ES","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\/es\/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":{"Escrito por":"Eugene van der Watt","Tiempo de lectura":"4 minutos"},"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":"es"},{"@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 ense\u00f1a a los modelos ling\u00fc\u00edsticos a pensar antes de hablar | 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":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/"]}]},{"@type":"ImageObject","inLanguage":"es","@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":"Su dosis diaria de noticias sobre 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":"es"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"es","@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":"es","@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 es ingeniero electr\u00f3nico y le encanta todo lo relacionado con la tecnolog\u00eda. Cuando descansa de consumir noticias sobre IA, lo encontrar\u00e1 jugando al billar.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/es\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts\/10866","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/comments?post=10866"}],"version-history":[{"count":5,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts\/10866\/revisions"}],"predecessor-version":[{"id":10873,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/posts\/10866\/revisions\/10873"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/media\/10869"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/media?parent=10866"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/categories?post=10866"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/es\/wp-json\/wp\/v2\/tags?post=10866"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}