{"id":928,"date":"2024-08-26T12:00:27","date_gmt":"2024-08-26T11:00:27","guid":{"rendered":"https:\/\/arien-euproject.eu\/?p=928"},"modified":"2025-06-06T16:02:35","modified_gmt":"2025-06-06T15:02:35","slug":"cea-listevalllm2024-prompter-un-tres-grand-modele-de-langue-ou-affiner-un-plus-petit","status":"publish","type":"post","link":"https:\/\/arien-euproject.eu\/?p=928","title":{"rendered":"CEA-List@EvalLLM2024: prompter un tr\u00e8s grand mod\u00e8le de langue ou affiner un plus petit?"},"content":{"rendered":"<p>The EvalLLM2024 challenge aims to evaluate the results of few-shot approaches to information extraction in French. Our contribution to this challenge tests two approaches: one exploits the available annotated data in the prompt of an LLM (in context learning) while the other fine-tunes a generic entity recognition model (GLiNER) by exploiting the annotated data. Our experiments show that this second approach obtains the best results, especially when enriched by a data augmentation step exploiting the annotation guide and LLMs for the generation of synthetic examples.<\/p>\n<p>&nbsp;<\/p>\n<p>View\u00a0<a href=\"https:\/\/zenodo.org\/records\/15607315\">ARIEN\u2019s Community<\/a>\u00a0on Zenodo to read the complete publication.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The EvalLLM2024 challenge aims to evaluate the results of few-shot approaches to information extraction in French. Our contribution to this challenge tests two approaches: one exploits<span class=\"excerpt-hellip\"> [\u2026]<\/span><\/p>\n","protected":false},"author":4,"featured_media":936,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[4],"tags":[],"class_list":["post-928","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-publications"],"acf":[],"_links":{"self":[{"href":"https:\/\/arien-euproject.eu\/index.php?rest_route=\/wp\/v2\/posts\/928","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/arien-euproject.eu\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/arien-euproject.eu\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/arien-euproject.eu\/index.php?rest_route=\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/arien-euproject.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=928"}],"version-history":[{"count":1,"href":"https:\/\/arien-euproject.eu\/index.php?rest_route=\/wp\/v2\/posts\/928\/revisions"}],"predecessor-version":[{"id":929,"href":"https:\/\/arien-euproject.eu\/index.php?rest_route=\/wp\/v2\/posts\/928\/revisions\/929"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/arien-euproject.eu\/index.php?rest_route=\/wp\/v2\/media\/936"}],"wp:attachment":[{"href":"https:\/\/arien-euproject.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=928"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/arien-euproject.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=928"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/arien-euproject.eu\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=928"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}