{"id":18165,"date":"2026-06-29T04:09:33","date_gmt":"2026-06-29T04:09:33","guid":{"rendered":"https:\/\/megagon.ai\/?post_type=publications&p=18165"},"modified":"2026-06-29T04:18:18","modified_gmt":"2026-06-29T04:18:18","slug":"extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks","status":"publish","type":"publications","link":"https:\/\/megagon.ai\/jp\/publications\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\/","title":{"rendered":"Extending omnes flores for the EvaLatin 2026 Dependency Parsing Tasks"},"template":"","publications-tags":[192],"conference-year":[353],"conference":[395],"class_list":["post-18165","publications","type-publications","status-publish","hentry","publications-tags-llm-nlp","conference-year-353","conference-lt4hala"],"yoast_head":"\nExtending omnes flores for the EvaLatin 2026 Dependency Parsing Tasks - Megagon<\/title>\n<meta name=\"description\" content=\"omnes flores is an NLP framework based on Universal Dependencies (UD) that utilizes multilingual Large Language Models (LLMs), and its default model is trained on data from 40 UD languages comprising 40 treebanks. For the EvaLatin 2026 Dependency Parsing Tasks, we extended the training data of omnes flores by incorporatingsix public Latin treebanks from UD and trained a dependency parsing model using the extended training data. The dependency parser of omnes flores normally takes a list of word FORM values as input. However, since the EvaLatin 2026 test data includes an UPOS column, we investigated whether incorporating both FORM and UPOSduring both training and inference could improve parsing accuracy. Our experiments show that training using both FORM and UPOS improves performance by 0.5-1.0 LAS points on Prose compared with training using only FORM, but decreases performance by 5 points on Poetry.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/megagon.ai\/jp\/publications\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\/\" \/>\n<meta property=\"og:locale\" content=\"ja_JP\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Tool-Induced Myopia (TIM) and the PyMath benchmark, accepted to ACL 2026 main conference\" \/>\n<meta property=\"og:description\" content=\"Tool-augmented LLMs can boost accuracy by calling external tools, but these gains don\u2019t usually reflect better reasoning. Our study shows that while tool use improves final-answer accuracy by up to 19.3 points, it comes at the cost of degraded reasoning quality.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/megagon.ai\/jp\/publications\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\/\" \/>\n<meta property=\"og:site_name\" content=\"Megagon\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/megagonlabs\/\" \/>\n<meta property=\"article:modified_time\" content=\"2026-06-29T04:18:18+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/megagon.ai\/wp-content\/uploads\/2025\/02\/Publications.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1600\" \/>\n\t<meta property=\"og:image:height\" content=\"900\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:title\" content=\"Tool-Induced Myopia (TIM) and the PyMath benchmark: paper accepted to ACL 2026 main conference\" \/>\n<meta name=\"twitter:description\" content=\"Tool-augmented LLMs can boost accuracy by calling external tools, but these gains don\u2019t usually reflect better reasoning. Our study shows that while tool use improves final-answer accuracy by up to 19.3 points, it comes at the cost of degraded reasoning quality.\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/megagon.ai\/wp-content\/uploads\/2025\/02\/Publications.png\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/publications\\\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\\\/\",\"url\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/publications\\\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\\\/\",\"name\":\"Extending omnes flores for the EvaLatin 2026 Dependency Parsing Tasks - Megagon\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/#website\"},\"datePublished\":\"2026-06-29T04:09:33+00:00\",\"dateModified\":\"2026-06-29T04:18:18+00:00\",\"description\":\"omnes flores is an NLP framework based on Universal Dependencies (UD) that utilizes multilingual Large Language Models (LLMs), and its default model is trained on data from 40 UD languages comprising 40 treebanks. For the EvaLatin 2026 Dependency Parsing Tasks, we extended the training data of omnes flores by incorporatingsix public Latin treebanks from UD and trained a dependency parsing model using the extended training data. The dependency parser of omnes flores normally takes a list of word FORM values as input. However, since the EvaLatin 2026 test data includes an UPOS column, we investigated whether incorporating both FORM and UPOSduring both training and inference could improve parsing accuracy. Our experiments show that training using both FORM and UPOS improves performance by 0.5-1.0 LAS points on Prose compared with training using only FORM, but decreases performance by 5 points on Poetry.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/publications\\\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\\\/#breadcrumb\"},\"inLanguage\":\"ja-JP\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/megagon.ai\\\/jp\\\/publications\\\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/publications\\\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Publications\",\"item\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/publications\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Extending omnes flores for the EvaLatin 2026 Dependency Parsing Tasks\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/#website\",\"url\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/\",\"name\":\"Megagon Labs\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ja-JP\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/megagon.ai\\\/jp\\\/#organization\",\"name\":\"Megagon Labs\",\"url\":\"https:\\\/\\\/megagon.ai\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/megagon.ai\\\/wp-content\\\/uploads\\\/2025\\\/02\\\/Logo-Megagon-Labs.webp\",\"caption\":\"Megagon Labs\"},\"image\":{\"url\":\"https:\\\/\\\/megagon.ai\\\/wp-content\\\/uploads\\\/2025\\\/02\\\/Logo-Megagon-Labs.webp\"},\"description\":\"Megagon Labs is an AI research organization conducting research in compound AI systems, large language models, data-AI symbiosis, and human-centered AI. Megagon Labs shares its findings with the broader community through open-source tools, datasets, publications, workshops, and an invited speaker series.\",\"sameAs\":[\"https:\\\/\\\/github.com\\\/megagonlabs\",\"https:\\\/\\\/twitter.com\\\/megagonlabs\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/megagon-labs\\\/\",\"https:\\\/\\\/www.facebook.com\\\/megagonlabs\\\/\"],\"address\":{\"@type\":\"PostalAddress\",\"streetAddress\":\"444 Castro Street\",\"addressLocality\":\"Mountain View\",\"addressRegion\":\"CA\",\"postalCode\":\"94041\",\"addressCountry\":\"US\"},\"contactPoint\":{\"@type\":\"ContactPoint\",\"email\":\"contactus@megagon.ai\",\"contactType\":\"general inquiries\"},\"parentOrganization\":{\"@type\":\"Organization\",\"name\":\"Recruit Holdings\",\"url\":\"https:\\\/\\\/recruit-holdings.com\\\/en\\\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Extending omnes flores for the EvaLatin 2026 Dependency Parsing Tasks - Megagon","description":"omnes flores is an NLP framework based on Universal Dependencies (UD) that utilizes multilingual Large Language Models (LLMs), and its default model is trained on data from 40 UD languages comprising 40 treebanks. For the EvaLatin 2026 Dependency Parsing Tasks, we extended the training data of omnes flores by incorporatingsix public Latin treebanks from UD and trained a dependency parsing model using the extended training data. The dependency parser of omnes flores normally takes a list of word FORM values as input. However, since the EvaLatin 2026 test data includes an UPOS column, we investigated whether incorporating both FORM and UPOSduring both training and inference could improve parsing accuracy. Our experiments show that training using both FORM and UPOS improves performance by 0.5-1.0 LAS points on Prose compared with training using only FORM, but decreases performance by 5 points on Poetry.","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:\/\/megagon.ai\/jp\/publications\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\/","og_locale":"ja_JP","og_type":"article","og_title":"Tool-Induced Myopia (TIM) and the PyMath benchmark, accepted to ACL 2026 main conference","og_description":"Tool-augmented LLMs can boost accuracy by calling external tools, but these gains don\u2019t usually reflect better reasoning. Our study shows that while tool use improves final-answer accuracy by up to 19.3 points, it comes at the cost of degraded reasoning quality.","og_url":"https:\/\/megagon.ai\/jp\/publications\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\/","og_site_name":"Megagon","article_publisher":"https:\/\/www.facebook.com\/megagonlabs\/","article_modified_time":"2026-06-29T04:18:18+00:00","og_image":[{"width":1600,"height":900,"url":"https:\/\/megagon.ai\/wp-content\/uploads\/2025\/02\/Publications.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_title":"Tool-Induced Myopia (TIM) and the PyMath benchmark: paper accepted to ACL 2026 main conference","twitter_description":"Tool-augmented LLMs can boost accuracy by calling external tools, but these gains don\u2019t usually reflect better reasoning. Our study shows that while tool use improves final-answer accuracy by up to 19.3 points, it comes at the cost of degraded reasoning quality.","twitter_image":"https:\/\/megagon.ai\/wp-content\/uploads\/2025\/02\/Publications.png","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/megagon.ai\/jp\/publications\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\/","url":"https:\/\/megagon.ai\/jp\/publications\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\/","name":"Extending omnes flores for the EvaLatin 2026 Dependency Parsing Tasks - Megagon","isPartOf":{"@id":"https:\/\/megagon.ai\/jp\/#website"},"datePublished":"2026-06-29T04:09:33+00:00","dateModified":"2026-06-29T04:18:18+00:00","description":"omnes flores is an NLP framework based on Universal Dependencies (UD) that utilizes multilingual Large Language Models (LLMs), and its default model is trained on data from 40 UD languages comprising 40 treebanks. For the EvaLatin 2026 Dependency Parsing Tasks, we extended the training data of omnes flores by incorporatingsix public Latin treebanks from UD and trained a dependency parsing model using the extended training data. The dependency parser of omnes flores normally takes a list of word FORM values as input. However, since the EvaLatin 2026 test data includes an UPOS column, we investigated whether incorporating both FORM and UPOSduring both training and inference could improve parsing accuracy. Our experiments show that training using both FORM and UPOS improves performance by 0.5-1.0 LAS points on Prose compared with training using only FORM, but decreases performance by 5 points on Poetry.","breadcrumb":{"@id":"https:\/\/megagon.ai\/jp\/publications\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\/#breadcrumb"},"inLanguage":"ja-JP","potentialAction":[{"@type":"ReadAction","target":["https:\/\/megagon.ai\/jp\/publications\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/megagon.ai\/jp\/publications\/extending-omnes-flores-for-the-evalatin-2026-dependency-parsing-tasks\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/megagon.ai\/jp\/"},{"@type":"ListItem","position":2,"name":"Publications","item":"https:\/\/megagon.ai\/jp\/publications\/"},{"@type":"ListItem","position":3,"name":"Extending omnes flores for the EvaLatin 2026 Dependency Parsing Tasks"}]},{"@type":"WebSite","@id":"https:\/\/megagon.ai\/jp\/#website","url":"https:\/\/megagon.ai\/jp\/","name":"Megagon Labs","description":"","publisher":{"@id":"https:\/\/megagon.ai\/jp\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/megagon.ai\/jp\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ja-JP"},{"@type":"Organization","@id":"https:\/\/megagon.ai\/jp\/#organization","name":"Megagon Labs","url":"https:\/\/megagon.ai\/","logo":{"@type":"ImageObject","url":"https:\/\/megagon.ai\/wp-content\/uploads\/2025\/02\/Logo-Megagon-Labs.webp","caption":"Megagon Labs"},"image":{"url":"https:\/\/megagon.ai\/wp-content\/uploads\/2025\/02\/Logo-Megagon-Labs.webp"},"description":"Megagon Labs is an AI research organization conducting research in compound AI systems, large language models, data-AI symbiosis, and human-centered AI. Megagon Labs shares its findings with the broader community through open-source tools, datasets, publications, workshops, and an invited speaker series.","sameAs":["https:\/\/github.com\/megagonlabs","https:\/\/twitter.com\/megagonlabs","https:\/\/www.linkedin.com\/company\/megagon-labs\/","https:\/\/www.facebook.com\/megagonlabs\/"],"address":{"@type":"PostalAddress","streetAddress":"444 Castro Street","addressLocality":"Mountain View","addressRegion":"CA","postalCode":"94041","addressCountry":"US"},"contactPoint":{"@type":"ContactPoint","email":"contactus@megagon.ai","contactType":"general inquiries"},"parentOrganization":{"@type":"Organization","name":"Recruit Holdings","url":"https:\/\/recruit-holdings.com\/en\/"}}]}},"_links":{"self":[{"href":"https:\/\/megagon.ai\/jp\/wp-json\/wp\/v2\/publications\/18165","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/megagon.ai\/jp\/wp-json\/wp\/v2\/publications"}],"about":[{"href":"https:\/\/megagon.ai\/jp\/wp-json\/wp\/v2\/types\/publications"}],"version-history":[{"count":1,"href":"https:\/\/megagon.ai\/jp\/wp-json\/wp\/v2\/publications\/18165\/revisions"}],"predecessor-version":[{"id":18166,"href":"https:\/\/megagon.ai\/jp\/wp-json\/wp\/v2\/publications\/18165\/revisions\/18166"}],"wp:attachment":[{"href":"https:\/\/megagon.ai\/jp\/wp-json\/wp\/v2\/media?parent=18165"}],"wp:term":[{"taxonomy":"publications-tags","embeddable":true,"href":"https:\/\/megagon.ai\/jp\/wp-json\/wp\/v2\/publications-tags?post=18165"},{"taxonomy":"conference-year","embeddable":true,"href":"https:\/\/megagon.ai\/jp\/wp-json\/wp\/v2\/conference-year?post=18165"},{"taxonomy":"conference","embeddable":true,"href":"https:\/\/megagon.ai\/jp\/wp-json\/wp\/v2\/conference?post=18165"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}