{"id":2438,"date":"2025-09-26T13:52:51","date_gmt":"2025-09-26T06:52:51","guid":{"rendered":"https:\/\/www.its.ac.id\/publikasi\/?p=2438"},"modified":"2025-09-26T13:52:51","modified_gmt":"2025-09-26T06:52:51","slug":"exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2","status":"publish","type":"post","link":"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/","title":{"rendered":"Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across Languages"},"content":{"rendered":"<section class=\"item authors\">\n<ul class=\"authors\">\n<li><span class=\"name\">Ubaidillah Ariq Prathama<\/span><span class=\"affiliation\">Institut Teknologi Bandung<\/span><\/li>\n<li><span class=\"name\">Ayu Purwarianti<\/span><span class=\"affiliation\">Institut Teknologi Bandung<\/span><\/li>\n<li><span class=\"name\">Samuel Cahyawijaya<\/span><span class=\"affiliation\">Cohere, United Kingdom<\/span><\/li>\n<\/ul>\n<\/section>\n<section class=\"item\"><span class=\"views\"><strong>Views:<\/strong>\u00a0331\u00a0<\/span><span class=\"views\"><strong>Downloads:<\/strong>\u00a0199<\/span><\/section>\n<section class=\"item doi\">\n<h2 class=\"label\">DOI:<\/h2>\n<p><span class=\"value\"><a href=\"https:\/\/doi.org\/10.12962\/j24068535.v23i2.a1323\">https:\/\/doi.org\/10.12962\/j24068535.v23i2.a1323<\/a><\/span><\/section>\n<section class=\"item abstract\">\n<h2 class=\"label\">Abstract<\/h2>\n<p>&nbsp;<\/p>\n<p>Most of past studies about in-context methods like in-context learning (ICL), cross-lingual ICL (X-ICL), and in-context alignment (ICA) come from older, unaligned large language models (LLMs). However, modern human-aligned LLMs are different; they come with chat-style prompt templates, are extensively human-aligned, and cover many more languages. We re-examined these in-context techniques using two recent, human-aligned multilingual LLMs. Our study covered 20 languages from seven different language families, representing high, mid, and low-resource levels. We tested how well these methods generalized using two tasks: topic classification (SIB-200) and machine reading comprehension (Belebele). We found that utilizing prompt templates significantly improves the performance of both ICL and X-ICL. Furthermore, ICA proves particularly effective for mid- and low-resource languages, boosting their f1-score by up to 6.1%. For X-ICL, choosing a source language that is linguistically similar to the target language, rather than defaulting to English, can lead to substantial gains, with improvements reaching up to 21.98%. Semantically similar ICL examples continue to be highly relevant for human-aligned LLMs, providing up to a 31.42% advantage over static examples. However, this gain decreases when using machine translation model to translate query from target language. These results collectively suggest that while modern human-aligned LLMs definitely benefit from in-context information, the extent of these gains is highly dependent on careful prompt design, the language&#8217;s resource level, language pairing, and the overall complexity of the task.<\/p>\n<\/section>\n<p><a href=\"https:\/\/juti.if.its.ac.id\/index.php\/juti\/article\/view\/1323\">https:\/\/juti.if.its.ac.id\/index.php\/juti\/article\/view\/1323<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Ubaidillah Ariq PrathamaInstitut Teknologi Bandung Ayu PurwariantiInstitut Teknologi Bandung Samuel CahyawijayaCohere, United Kingdom Views:\u00a0331\u00a0Downloads:\u00a0199 DOI: https:\/\/doi.org\/10.12962\/j24068535.v23i2.a1323 Abstract &nbsp; Most of past studies about in-context methods like in-context learning (ICL), cross-lingual ICL (X-ICL), and in-context alignment (ICA) come from older, unaligned large language models (LLMs). However, modern human-aligned LLMs are different; they come with chat-style prompt [&hellip;]<\/p>\n","protected":false},"author":250,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_joinchat":[],"footnotes":""},"categories":[258],"tags":[],"class_list":["post-2438","post","type-post","status-publish","format-standard","hentry","category-juti-journal"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.1.1 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across Languages - IJC ( ITS Journal Center )<\/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:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across Languages - IJC ( ITS Journal Center )\" \/>\n<meta property=\"og:description\" content=\"Ubaidillah Ariq PrathamaInstitut Teknologi Bandung Ayu PurwariantiInstitut Teknologi Bandung Samuel CahyawijayaCohere, United Kingdom Views:\u00a0331\u00a0Downloads:\u00a0199 DOI: https:\/\/doi.org\/10.12962\/j24068535.v23i2.a1323 Abstract &nbsp; Most of past studies about in-context methods like in-context learning (ICL), cross-lingual ICL (X-ICL), and in-context alignment (ICA) come from older, unaligned large language models (LLMs). However, modern human-aligned LLMs are different; they come with chat-style prompt [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/\" \/>\n<meta property=\"og:site_name\" content=\"IJC ( ITS Journal Center )\" \/>\n<meta property=\"article:published_time\" content=\"2025-09-26T06:52:51+00:00\" \/>\n<meta name=\"author\" content=\"itspublikasi\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"itspublikasi\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/\"},\"author\":{\"name\":\"itspublikasi\",\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/#\/schema\/person\/1241b8776d05c54fbc628c0a83d59e3c\"},\"headline\":\"Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across Languages\",\"datePublished\":\"2025-09-26T06:52:51+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/\"},\"wordCount\":277,\"commentCount\":0,\"articleSection\":[\"juti journal\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/\",\"url\":\"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/\",\"name\":\"Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across Languages - IJC ( ITS Journal Center )\",\"isPartOf\":{\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/#website\"},\"datePublished\":\"2025-09-26T06:52:51+00:00\",\"author\":{\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/#\/schema\/person\/1241b8776d05c54fbc628c0a83d59e3c\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.its.ac.id\/publikasi\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across Languages\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/#website\",\"url\":\"https:\/\/www.its.ac.id\/publikasi\/\",\"name\":\"IJC ( ITS Journal Center )\",\"description\":\"Institut Teknologi Sepuluh Nopember\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.its.ac.id\/publikasi\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/#\/schema\/person\/1241b8776d05c54fbc628c0a83d59e3c\",\"name\":\"itspublikasi\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.its.ac.id\/publikasi\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/1c672fdec2c22686bbf54db48608a7cbb61f01783efa5776676dd183144eeffd?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/1c672fdec2c22686bbf54db48608a7cbb61f01783efa5776676dd183144eeffd?s=96&d=mm&r=g\",\"caption\":\"itspublikasi\"},\"url\":\"https:\/\/www.its.ac.id\/publikasi\/author\/itspublikasi\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across Languages - IJC ( ITS Journal Center )","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:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/","og_locale":"en_US","og_type":"article","og_title":"Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across Languages - IJC ( ITS Journal Center )","og_description":"Ubaidillah Ariq PrathamaInstitut Teknologi Bandung Ayu PurwariantiInstitut Teknologi Bandung Samuel CahyawijayaCohere, United Kingdom Views:\u00a0331\u00a0Downloads:\u00a0199 DOI: https:\/\/doi.org\/10.12962\/j24068535.v23i2.a1323 Abstract &nbsp; Most of past studies about in-context methods like in-context learning (ICL), cross-lingual ICL (X-ICL), and in-context alignment (ICA) come from older, unaligned large language models (LLMs). However, modern human-aligned LLMs are different; they come with chat-style prompt [&hellip;]","og_url":"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/","og_site_name":"IJC ( ITS Journal Center )","article_published_time":"2025-09-26T06:52:51+00:00","author":"itspublikasi","twitter_card":"summary_large_image","twitter_misc":{"Written by":"itspublikasi"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/#article","isPartOf":{"@id":"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/"},"author":{"name":"itspublikasi","@id":"https:\/\/www.its.ac.id\/publikasi\/#\/schema\/person\/1241b8776d05c54fbc628c0a83d59e3c"},"headline":"Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across Languages","datePublished":"2025-09-26T06:52:51+00:00","mainEntityOfPage":{"@id":"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/"},"wordCount":277,"commentCount":0,"articleSection":["juti journal"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/","url":"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/","name":"Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across Languages - IJC ( ITS Journal Center )","isPartOf":{"@id":"https:\/\/www.its.ac.id\/publikasi\/#website"},"datePublished":"2025-09-26T06:52:51+00:00","author":{"@id":"https:\/\/www.its.ac.id\/publikasi\/#\/schema\/person\/1241b8776d05c54fbc628c0a83d59e3c"},"breadcrumb":{"@id":"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.its.ac.id\/publikasi\/en\/2025\/09\/26\/exploring-the-effectiveness-of-in-context-methods-in-human-aligned-large-language-models-across-languages-2\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.its.ac.id\/publikasi\/"},{"@type":"ListItem","position":2,"name":"Exploring The Effectiveness of In-Context Methods in Human-Aligned Large Language Models Across Languages"}]},{"@type":"WebSite","@id":"https:\/\/www.its.ac.id\/publikasi\/#website","url":"https:\/\/www.its.ac.id\/publikasi\/","name":"IJC ( ITS Journal Center )","description":"Institut Teknologi Sepuluh Nopember","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.its.ac.id\/publikasi\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.its.ac.id\/publikasi\/#\/schema\/person\/1241b8776d05c54fbc628c0a83d59e3c","name":"itspublikasi","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.its.ac.id\/publikasi\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/1c672fdec2c22686bbf54db48608a7cbb61f01783efa5776676dd183144eeffd?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/1c672fdec2c22686bbf54db48608a7cbb61f01783efa5776676dd183144eeffd?s=96&d=mm&r=g","caption":"itspublikasi"},"url":"https:\/\/www.its.ac.id\/publikasi\/author\/itspublikasi\/"}]}},"_links":{"self":[{"href":"https:\/\/www.its.ac.id\/publikasi\/wp-json\/wp\/v2\/posts\/2438","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.its.ac.id\/publikasi\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.its.ac.id\/publikasi\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.its.ac.id\/publikasi\/wp-json\/wp\/v2\/users\/250"}],"replies":[{"embeddable":true,"href":"https:\/\/www.its.ac.id\/publikasi\/wp-json\/wp\/v2\/comments?post=2438"}],"version-history":[{"count":1,"href":"https:\/\/www.its.ac.id\/publikasi\/wp-json\/wp\/v2\/posts\/2438\/revisions"}],"predecessor-version":[{"id":2439,"href":"https:\/\/www.its.ac.id\/publikasi\/wp-json\/wp\/v2\/posts\/2438\/revisions\/2439"}],"wp:attachment":[{"href":"https:\/\/www.its.ac.id\/publikasi\/wp-json\/wp\/v2\/media?parent=2438"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.its.ac.id\/publikasi\/wp-json\/wp\/v2\/categories?post=2438"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.its.ac.id\/publikasi\/wp-json\/wp\/v2\/tags?post=2438"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}