{"id":40060,"date":"2026-01-16T15:38:04","date_gmt":"2026-01-16T14:38:04","guid":{"rendered":"https:\/\/kinit.sk\/?post_type=publication&#038;p=40060"},"modified":"2026-05-14T14:42:54","modified_gmt":"2026-05-14T12:42:54","slug":"investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection","status":"publish","type":"publication","link":"https:\/\/kinit.sk\/sk\/publikacia\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\/","title":{"rendered":"Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection"},"content":{"rendered":"<div id=\"\" class=\"element core-paragraph\">\n<p><strong>Vykopal, I., Karamolegkou, A.<strong><strong><sup>1<\/sup><\/strong><\/strong>, Kopcan, J.,<\/strong> <strong>Peng, Q.<strong><sup>1<\/sup><\/strong>, Javurek, T., Gregor, M., Simko, M.<\/strong><\/p>\n<\/div>\n\n<div id=\"\" class=\"element core-paragraph\">\n<p class=\"has-small-font-size\"><em><sup>1<\/sup> University of Copenhagen, Denmark, Copenhagen<\/em><\/p>\n<\/div>\n\n<div id=\"\" class=\"element core-paragraph\">\n<p>Multilingual Large Language Models (LLMs) offer powerful capabilities for cross-lingual fact-checking. However, these models often exhibit language bias, performing disproportionately better on high-resource languages such as English than on low-resource counterparts. We also present and inspect a novel concept &#8211; retrieval bias, when information retrieval systems tend to favor certain information over others, leaving the retrieval process skewed. In this paper, we study language and retrieval bias in the context of Previously Fact-Checked Claim Detection (PFCD). We evaluate six open-source multilingual LLMs across 20 languages using a fully multilingual prompting strategy, leveraging the AMC-16K dataset. By translating task prompts into each language, we uncover disparities in monolingual and cross-lingual performance and identify key trends based on model family, size, and prompting strategy. Our findings highlight persistent bias in LLM behavior and offer recommendations for improving equity in multilingual fact-checking. To investigate retrieval bias, we employed multilingual embedding models and look into the frequency of retrieved claims. Our analysis reveals that certain claims are retrieved disproportionately across different posts, leading to inflated retrieval performance for popular claims while under-representing less common ones.<\/p>\n<\/div>\n\n<div id=\"\" class=\"element core-paragraph\">\n<p>Cite: Vykopal, I., Karamolegkou, A., Kopcan, J., Peng, Q., Javurek, T., Gregor, M., Simko, M. Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection. In <em>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). <\/em>Rabat, Morocco. Association for Computational Linguistics. 2026. DOI: <a href=\"https:\/\/doi.org\/10.18653\/v1\/2026.eacl-long.240\">10.18653\/v1\/2026.eacl-long.240<\/a><\/p>\n<\/div>","protected":false},"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"categories":[76,520],"class_list":["post-40060","publication","type-publication","status-publish","hentry","category-natural-language-processing-sk","category-2025-sk"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.5 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection - KInIT<\/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:\/\/kinit.sk\/sk\/publikacia\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\/\" \/>\n<meta property=\"og:locale\" content=\"sk_SK\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection - KInIT\" \/>\n<meta property=\"og:description\" content=\"Vykopal, I., Karamolegkou, A.1, Kopcan, J., Peng, Q.1, Javurek, T., Gregor, M., Simko, M. 1 University of Copenhagen, Denmark, Copenhagen Multilingual Large Language Models (LLMs) offer powerful capabilities for cross-lingual...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/kinit.sk\/sk\/publikacia\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\/\" \/>\n<meta property=\"og:site_name\" content=\"KInIT\" \/>\n<meta property=\"article:modified_time\" content=\"2026-05-14T12:42:54+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/kinit.sk\/wp-content\/uploads\/2021\/03\/KINIT_Sharepic.png\" \/>\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\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@kinit\" \/>\n<meta name=\"twitter:label1\" content=\"Predpokladan\u00fd \u010das \u010d\u00edtania\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 min\u00faty\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/publikacia\\\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\\\/\",\"url\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/publikacia\\\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\\\/\",\"name\":\"Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection - KInIT\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/kinit.sk\\\/#website\"},\"datePublished\":\"2026-01-16T14:38:04+00:00\",\"dateModified\":\"2026-05-14T12:42:54+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/publikacia\\\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\\\/#breadcrumb\"},\"inLanguage\":\"sk-SK\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/kinit.sk\\\/sk\\\/publikacia\\\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/publikacia\\\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Natural Language Processing\",\"item\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/category\\\/natural-language-processing-sk\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/kinit.sk\\\/#website\",\"url\":\"https:\\\/\\\/kinit.sk\\\/\",\"name\":\"KInIT\",\"description\":\"Vyu\u017e\u00edvame v\u00fdskum pre \u013eud\u00ed a priemysel\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/kinit.sk\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"sk-SK\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection - KInIT","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:\/\/kinit.sk\/sk\/publikacia\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\/","og_locale":"sk_SK","og_type":"article","og_title":"Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection - KInIT","og_description":"Vykopal, I., Karamolegkou, A.1, Kopcan, J., Peng, Q.1, Javurek, T., Gregor, M., Simko, M. 1 University of Copenhagen, Denmark, Copenhagen Multilingual Large Language Models (LLMs) offer powerful capabilities for cross-lingual...","og_url":"https:\/\/kinit.sk\/sk\/publikacia\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\/","og_site_name":"KInIT","article_modified_time":"2026-05-14T12:42:54+00:00","og_image":[{"width":1200,"height":628,"url":"https:\/\/kinit.sk\/wp-content\/uploads\/2021\/03\/KINIT_Sharepic.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_site":"@kinit","twitter_misc":{"Predpokladan\u00fd \u010das \u010d\u00edtania":"2 min\u00faty"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/kinit.sk\/sk\/publikacia\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\/","url":"https:\/\/kinit.sk\/sk\/publikacia\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\/","name":"Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection - KInIT","isPartOf":{"@id":"https:\/\/kinit.sk\/#website"},"datePublished":"2026-01-16T14:38:04+00:00","dateModified":"2026-05-14T12:42:54+00:00","breadcrumb":{"@id":"https:\/\/kinit.sk\/sk\/publikacia\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\/#breadcrumb"},"inLanguage":"sk-SK","potentialAction":[{"@type":"ReadAction","target":["https:\/\/kinit.sk\/sk\/publikacia\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/kinit.sk\/sk\/publikacia\/investigating-language-and-retrieval-bias-in-multilingual-previously-fact-checked-claim-detection\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/kinit.sk\/sk\/"},{"@type":"ListItem","position":2,"name":"Natural Language Processing","item":"https:\/\/kinit.sk\/sk\/category\/natural-language-processing-sk\/"},{"@type":"ListItem","position":3,"name":"Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection"}]},{"@type":"WebSite","@id":"https:\/\/kinit.sk\/#website","url":"https:\/\/kinit.sk\/","name":"KInIT","description":"Vyu\u017e\u00edvame v\u00fdskum pre \u013eud\u00ed a priemysel","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/kinit.sk\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"sk-SK"}]}},"_links":{"self":[{"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/publication\/40060","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/types\/publication"}],"version-history":[{"count":1,"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/publication\/40060\/revisions"}],"predecessor-version":[{"id":42446,"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/publication\/40060\/revisions\/42446"}],"wp:attachment":[{"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/media?parent=40060"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/categories?post=40060"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}