{"id":7114,"date":"2023-05-23T14:49:29","date_gmt":"2023-05-23T14:49:29","guid":{"rendered":"https:\/\/novelis.io\/?post_type=scientific-pub&#038;p=7114"},"modified":"2023-09-25T15:14:15","modified_gmt":"2023-09-25T15:14:15","slug":"gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero","status":"publish","type":"scientific-pub","link":"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/","title":{"rendered":"GPT-3.5 vs GPT-4 : \u00e9valuation des performances de raisonnement de ChatGPT dans le cadre de l&rsquo;apprentissage \u00e0 partir de z\u00e9ro"},"content":{"rendered":"\n<p>D\u00e9couvrez la premi\u00e8re version de notre publication scientifique \u00ab\u00a0GPT-3.5 vs GPT-4: Evaluating ChatGPT&rsquo;s Reasoning Performance in Zero-shot Learning\u00a0\u00bb\u00a0publi\u00e9 dans <a href=\"https:\/\/arxiv.org\/abs\/2305.12477\" target=\"_blank\" rel=\"noopener\">arxiv<\/a>, plateforme largement reconnue pour le partage de pr\u00e9prints et d&rsquo;articles scientifiques. Cet article r\u00e9dig\u00e9 en anglais fait actuellement l&rsquo;objet d&rsquo;un processus de r\u00e9vision rigoureux. <\/p>\n\n\n\n<p>Merci \u00e0 l\u2019<a href=\"https:\/\/novelis.io\/fr\/laboratoire-rd\/\">\u00e9quipe de recherche de Novelis<\/a>&nbsp;&#8211; notamment Jessica&nbsp;L\u00f3pez Espejel,&nbsp;Mahaman Sanoussi&nbsp;Yahaya Alassan,&nbsp;El Mehdi&nbsp;Chouham,&nbsp;El Hassane&nbsp;Ettifouri, Walid Dahhane &#8211; pour son savoir-faire et son expertise.<\/p>\n\n\n\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button\"><a class=\"wp-block-button__link wp-element-button\" href=\"https:\/\/arxiv.org\/pdf\/2305.12477.pdf\" target=\"_blank\" rel=\"noopener\">Lire l&rsquo;article complet<\/a><\/div>\n<\/div>\n\n\n\n<div style=\"height:100px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"a-propos-de-l-etude\">A propos<\/h2>\n\n\n\n<p>\u201cLarge Language Models (LLMs) have exhibited remarkable performance on various Natural Language Processing (NLP) tasks. However, there is a current hot debate regarding their reasoning capacity. In this paper, we examine the performance of GPT-3.5 and GPT-4 models, by performing a thorough technical evaluation on different reasoning tasks across eleven distinct datasets. Our findings show that GPT-4 outperforms GPT-3.5 in zero-shot learning throughout almost all evaluated tasks. In addition, we note that both models exhibit limited performance in Inductive, Mathematical, and Multi-hop Reasoning Tasks. While it may seem intuitive that the GPT-4 model would outperform GPT-3.5 given its size and efficiency in various NLP tasks, our paper offers empirical evidence to support this claim. We provide a detailed and comprehensive analysis of the results from both models to further support our findings. In addition, we propose a set of engineered prompts that improves performance of both models on zero-shot learning.\u201d<\/p>\n\n\n\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\"><\/div>\n\n\n\n<div style=\"height:49px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><strong>arXiv est une archive ouverte de pr\u00e9publications \u00e9lectroniques d&rsquo;articles scientifiques dans diff\u00e9rents domaines techniques, tels que la physique, les math\u00e9matiques, l&rsquo;informatique et bien plus encore, gratuitement accessible par Internet.<\/strong><\/p>\n\n\n\n<p><strong>L&rsquo;universit\u00e9 Cornell est une universit\u00e9 priv\u00e9e am\u00e9ricaine situ\u00e9e principalement dans la ville d&rsquo;Ithaca dans l\u2019\u00c9tat de New York.<\/strong><\/p>\n","protected":false},"featured_media":7115,"template":"","categories":[24],"custom_tag":[378,458,457],"class_list":["post-7114","scientific-pub","type-scientific-pub","status-publish","has-post-thumbnail","hentry","category-publication-scientifique","custom_tag-chatgpt-2","custom_tag-gpt-3-5-fr","custom_tag-gpt-4-fr"],"acf":{"externel_link":"","summary":"","filter_opacity":"70","subtitle":"","reading_time":"","authors":"","document_to_download":{"upload_a_file":false,"download_without_form":false,"file":false,"url":""}},"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.6 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>GPT-3.5 vs GPT-4 : \u00e9valuation des performances de ChatGPT<\/title>\n<meta name=\"description\" content=\"D\u00e9couvrez notre article sur les \u00e9volutions de GPT-3.5 vs GPT-4 publi\u00e9 dans arxiv et repris sur le site de Cornell University.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"GPT-3.5 vs GPT-4 : \u00e9valuation des performances de ChatGPT\" \/>\n<meta property=\"og:description\" content=\"D\u00e9couvrez notre article sur les \u00e9volutions de GPT-3.5 vs GPT-4 publi\u00e9 dans arxiv et repris sur le site de Cornell University.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/\" \/>\n<meta property=\"og:site_name\" content=\"Novelis innovation\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/novelis.io\" \/>\n<meta property=\"article:modified_time\" content=\"2023-09-25T15:14:15+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/novelis.io\/wp-content\/uploads\/2023\/05\/BLOG-1200-\u00d7-628-px-5.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"628\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@novelis_io\" \/>\n<meta name=\"twitter:label1\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/\",\"url\":\"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/\",\"name\":\"GPT-3.5 vs GPT-4 : \u00e9valuation des performances de ChatGPT\",\"isPartOf\":{\"@id\":\"https:\/\/novelis.io\/fr\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/novelis.io\/wp-content\/uploads\/2023\/05\/BLOG-1200-\u00d7-628-px-5.jpg\",\"datePublished\":\"2023-05-23T14:49:29+00:00\",\"dateModified\":\"2023-09-25T15:14:15+00:00\",\"description\":\"D\u00e9couvrez notre article sur les \u00e9volutions de GPT-3.5 vs GPT-4 publi\u00e9 dans arxiv et repris sur le site de Cornell University.\",\"breadcrumb\":{\"@id\":\"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/#primaryimage\",\"url\":\"https:\/\/novelis.io\/wp-content\/uploads\/2023\/05\/BLOG-1200-\u00d7-628-px-5.jpg\",\"contentUrl\":\"https:\/\/novelis.io\/wp-content\/uploads\/2023\/05\/BLOG-1200-\u00d7-628-px-5.jpg\",\"width\":1200,\"height\":628,\"caption\":\"chat gpt\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Accueil\",\"item\":\"https:\/\/novelis.io\/fr\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"GPT-3.5 vs GPT-4 : \u00e9valuation des performances de raisonnement de ChatGPT dans le cadre de l&rsquo;apprentissage \u00e0 partir de z\u00e9ro\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/novelis.io\/fr\/#website\",\"url\":\"https:\/\/novelis.io\/fr\/\",\"name\":\"Novelis innovation\",\"description\":\"Novelis innovation\",\"publisher\":{\"@id\":\"https:\/\/novelis.io\/fr\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/novelis.io\/fr\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/novelis.io\/fr\/#organization\",\"name\":\"Novelis innovation\",\"url\":\"https:\/\/novelis.io\/fr\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/novelis.io\/fr\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/novelis.io\/wp-content\/uploads\/2021\/12\/logo-1.png\",\"contentUrl\":\"https:\/\/novelis.io\/wp-content\/uploads\/2021\/12\/logo-1.png\",\"width\":479,\"height\":98,\"caption\":\"Novelis innovation\"},\"image\":{\"@id\":\"https:\/\/novelis.io\/fr\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/novelis.io\",\"https:\/\/x.com\/novelis_io\",\"https:\/\/www.linkedin.com\/company\/novelis-consulting\/\",\"https:\/\/www.youtube.com\/channel\/UCJ5eJR22n2GtfKaTWueWRPQ\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"GPT-3.5 vs GPT-4 : \u00e9valuation des performances de ChatGPT","description":"D\u00e9couvrez notre article sur les \u00e9volutions de GPT-3.5 vs GPT-4 publi\u00e9 dans arxiv et repris sur le site de Cornell University.","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:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/","og_locale":"fr_FR","og_type":"article","og_title":"GPT-3.5 vs GPT-4 : \u00e9valuation des performances de ChatGPT","og_description":"D\u00e9couvrez notre article sur les \u00e9volutions de GPT-3.5 vs GPT-4 publi\u00e9 dans arxiv et repris sur le site de Cornell University.","og_url":"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/","og_site_name":"Novelis innovation","article_publisher":"https:\/\/www.facebook.com\/novelis.io","article_modified_time":"2023-09-25T15:14:15+00:00","og_image":[{"width":1200,"height":628,"url":"https:\/\/novelis.io\/wp-content\/uploads\/2023\/05\/BLOG-1200-\u00d7-628-px-5.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_site":"@novelis_io","twitter_misc":{"Dur\u00e9e de lecture estim\u00e9e":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/","url":"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/","name":"GPT-3.5 vs GPT-4 : \u00e9valuation des performances de ChatGPT","isPartOf":{"@id":"https:\/\/novelis.io\/fr\/#website"},"primaryImageOfPage":{"@id":"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/#primaryimage"},"image":{"@id":"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/#primaryimage"},"thumbnailUrl":"https:\/\/novelis.io\/wp-content\/uploads\/2023\/05\/BLOG-1200-\u00d7-628-px-5.jpg","datePublished":"2023-05-23T14:49:29+00:00","dateModified":"2023-09-25T15:14:15+00:00","description":"D\u00e9couvrez notre article sur les \u00e9volutions de GPT-3.5 vs GPT-4 publi\u00e9 dans arxiv et repris sur le site de Cornell University.","breadcrumb":{"@id":"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/#primaryimage","url":"https:\/\/novelis.io\/wp-content\/uploads\/2023\/05\/BLOG-1200-\u00d7-628-px-5.jpg","contentUrl":"https:\/\/novelis.io\/wp-content\/uploads\/2023\/05\/BLOG-1200-\u00d7-628-px-5.jpg","width":1200,"height":628,"caption":"chat gpt"},{"@type":"BreadcrumbList","@id":"https:\/\/novelis.io\/fr\/scientific-pub\/gpt-3-5-vs-gpt-4-evaluation-des-performances-de-raisonnement-de-chatgpt-dans-le-cadre-de-lapprentissage-a-partir-de-zero\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Accueil","item":"https:\/\/novelis.io\/fr\/"},{"@type":"ListItem","position":2,"name":"GPT-3.5 vs GPT-4 : \u00e9valuation des performances de raisonnement de ChatGPT dans le cadre de l&rsquo;apprentissage \u00e0 partir de z\u00e9ro"}]},{"@type":"WebSite","@id":"https:\/\/novelis.io\/fr\/#website","url":"https:\/\/novelis.io\/fr\/","name":"Novelis innovation","description":"Novelis innovation","publisher":{"@id":"https:\/\/novelis.io\/fr\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/novelis.io\/fr\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/novelis.io\/fr\/#organization","name":"Novelis innovation","url":"https:\/\/novelis.io\/fr\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/novelis.io\/fr\/#\/schema\/logo\/image\/","url":"https:\/\/novelis.io\/wp-content\/uploads\/2021\/12\/logo-1.png","contentUrl":"https:\/\/novelis.io\/wp-content\/uploads\/2021\/12\/logo-1.png","width":479,"height":98,"caption":"Novelis innovation"},"image":{"@id":"https:\/\/novelis.io\/fr\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/novelis.io","https:\/\/x.com\/novelis_io","https:\/\/www.linkedin.com\/company\/novelis-consulting\/","https:\/\/www.youtube.com\/channel\/UCJ5eJR22n2GtfKaTWueWRPQ"]}]}},"_links":{"self":[{"href":"https:\/\/novelis.io\/fr\/wp-json\/wp\/v2\/scientific-pub\/7114"}],"collection":[{"href":"https:\/\/novelis.io\/fr\/wp-json\/wp\/v2\/scientific-pub"}],"about":[{"href":"https:\/\/novelis.io\/fr\/wp-json\/wp\/v2\/types\/scientific-pub"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/novelis.io\/fr\/wp-json\/wp\/v2\/media\/7115"}],"wp:attachment":[{"href":"https:\/\/novelis.io\/fr\/wp-json\/wp\/v2\/media?parent=7114"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/novelis.io\/fr\/wp-json\/wp\/v2\/categories?post=7114"},{"taxonomy":"custom_tag","embeddable":true,"href":"https:\/\/novelis.io\/fr\/wp-json\/wp\/v2\/custom_tag?post=7114"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}