{"id":78436,"date":"2026-03-23T14:37:32","date_gmt":"2026-03-23T14:37:32","guid":{"rendered":"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/"},"modified":"2026-03-23T14:37:32","modified_gmt":"2026-03-23T14:37:32","slug":"a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness","status":"publish","type":"post","link":"https:\/\/youzum.net\/fr\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/","title":{"rendered":"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness"},"content":{"rendered":"<p>arXiv:2601.03273v2 Announce Type: replace<br \/>\nAbstract: As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholding appropriate censorship boundaries has never been greater. While existing LLMs can detect dangerous or unsafe content, they often struggle with nuanced cases such as implicit offensiveness, subtle gender and racial biases, and jailbreak prompts, due to the subjective and context-dependent nature of these issues. Furthermore, their heavy reliance on training data can reinforce societal biases, resulting in inconsistent and ethically problematic outputs. To address these challenges, we introduce GuardEval, a unified multi-perspective benchmark dataset designed for both training and evaluation, containing 106 fine-grained categories spanning human emotions, offensive and hateful language, gender and racial bias, and broader safety concerns. We also present GemmaGuard (GGuard), a Quantized Low-Rank Adaptation (QLoRA), fine-tuned version of Gemma3-12B trained on GuardEval, to assess content moderation with fine-grained labels. Our evaluation shows that GGuard achieves a macro F1 score of 0.832, substantially outperforming leading moderation models, including OpenAI Moderator (0.64) and Llama Guard (0.61). We show that multi-perspective, human-centered safety benchmarks are critical for mitigating inconsistent moderation decisions. GuardEval and GGuard together demonstrate that diverse, representative data materially improve safety, and adversarial robustness on complex, borderline cases.<\/p>","protected":false},"excerpt":{"rendered":"<p>arXiv:2601.03273v2 Announce Type: replace Abstract: As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholding appropriate censorship boundaries has never been greater. While existing LLMs can detect dangerous or unsafe content, they often struggle with nuanced cases such as implicit offensiveness, subtle gender and racial biases, and jailbreak prompts, due to the subjective and context-dependent nature of these issues. Furthermore, their heavy reliance on training data can reinforce societal biases, resulting in inconsistent and ethically problematic outputs. To address these challenges, we introduce GuardEval, a unified multi-perspective benchmark dataset designed for both training and evaluation, containing 106 fine-grained categories spanning human emotions, offensive and hateful language, gender and racial bias, and broader safety concerns. We also present GemmaGuard (GGuard), a Quantized Low-Rank Adaptation (QLoRA), fine-tuned version of Gemma3-12B trained on GuardEval, to assess content moderation with fine-grained labels. Our evaluation shows that GGuard achieves a macro F1 score of 0.832, substantially outperforming leading moderation models, including OpenAI Moderator (0.64) and Llama Guard (0.61). We show that multi-perspective, human-centered safety benchmarks are critical for mitigating inconsistent moderation decisions. GuardEval and GGuard together demonstrate that diverse, representative data materially improve safety, and adversarial robustness on complex, borderline cases.<\/p>","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"pmpro_default_level":"","site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"_pvb_checkbox_block_on_post":false,"footnotes":""},"categories":[52,5,7,1],"tags":[],"class_list":["post-78436","post","type-post","status-publish","format-standard","hentry","category-ai-club","category-committee","category-news","category-uncategorized","pmpro-has-access"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness - YouZum<\/title>\n<meta name=\"description\" content=\"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/youzum.net\/fr\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness - YouZum\" \/>\n<meta property=\"og:description\" content=\"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19\" \/>\n<meta property=\"og:url\" content=\"https:\/\/youzum.net\/fr\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/\" \/>\n<meta property=\"og:site_name\" content=\"YouZum\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/DroneAssociationTH\/\" \/>\n<meta property=\"article:published_time\" content=\"2026-03-23T14:37:32+00:00\" \/>\n<meta name=\"author\" content=\"admin NU\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin NU\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/\"},\"author\":{\"name\":\"admin NU\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c\"},\"headline\":\"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness\",\"datePublished\":\"2026-03-23T14:37:32+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/\"},\"wordCount\":224,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#organization\"},\"articleSection\":[\"AI\",\"Committee\",\"News\",\"Uncategorized\"],\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/\",\"url\":\"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/\",\"name\":\"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness - YouZum\",\"isPartOf\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#website\"},\"datePublished\":\"2026-03-23T14:37:32+00:00\",\"description\":\"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19\",\"breadcrumb\":{\"@id\":\"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/youzum.net\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/yousum.gpucore.co\/#website\",\"url\":\"https:\/\/yousum.gpucore.co\/\",\"name\":\"YouSum\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/yousum.gpucore.co\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/yousum.gpucore.co\/#organization\",\"name\":\"Drone Association Thailand\",\"url\":\"https:\/\/yousum.gpucore.co\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png\",\"contentUrl\":\"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png\",\"width\":300,\"height\":300,\"caption\":\"Drone Association Thailand\"},\"image\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/DroneAssociationTH\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c\",\"name\":\"admin NU\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png\",\"contentUrl\":\"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png\",\"caption\":\"admin NU\"},\"url\":\"https:\/\/youzum.net\/fr\/members\/adminnu\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness - YouZum","description":"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19","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:\/\/youzum.net\/fr\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/","og_locale":"fr_FR","og_type":"article","og_title":"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness - YouZum","og_description":"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19","og_url":"https:\/\/youzum.net\/fr\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/","og_site_name":"YouZum","article_publisher":"https:\/\/www.facebook.com\/DroneAssociationTH\/","article_published_time":"2026-03-23T14:37:32+00:00","author":"admin NU","twitter_card":"summary_large_image","twitter_misc":{"\u00c9crit par":"admin NU","Dur\u00e9e de lecture estim\u00e9e":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/#article","isPartOf":{"@id":"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/"},"author":{"name":"admin NU","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c"},"headline":"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness","datePublished":"2026-03-23T14:37:32+00:00","mainEntityOfPage":{"@id":"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/"},"wordCount":224,"commentCount":0,"publisher":{"@id":"https:\/\/yousum.gpucore.co\/#organization"},"articleSection":["AI","Committee","News","Uncategorized"],"inLanguage":"fr-FR","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/","url":"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/","name":"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness - YouZum","isPartOf":{"@id":"https:\/\/yousum.gpucore.co\/#website"},"datePublished":"2026-03-23T14:37:32+00:00","description":"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19","breadcrumb":{"@id":"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/youzum.net\/a-multi-perspective-benchmark-and-moderation-model-for-evaluating-safety-and-adversarial-robustness\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/youzum.net\/"},{"@type":"ListItem","position":2,"name":"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness"}]},{"@type":"WebSite","@id":"https:\/\/yousum.gpucore.co\/#website","url":"https:\/\/yousum.gpucore.co\/","name":"YouSum","description":"","publisher":{"@id":"https:\/\/yousum.gpucore.co\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/yousum.gpucore.co\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/yousum.gpucore.co\/#organization","name":"Drone Association Thailand","url":"https:\/\/yousum.gpucore.co\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/","url":"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png","contentUrl":"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png","width":300,"height":300,"caption":"Drone Association Thailand"},"image":{"@id":"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/DroneAssociationTH\/"]},{"@type":"Person","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c","name":"admin NU","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/person\/image\/","url":"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png","contentUrl":"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png","caption":"admin NU"},"url":"https:\/\/youzum.net\/fr\/members\/adminnu\/"}]}},"rttpg_featured_image_url":null,"rttpg_author":{"display_name":"admin NU","author_link":"https:\/\/youzum.net\/fr\/members\/adminnu\/"},"rttpg_comment":0,"rttpg_category":"<a href=\"https:\/\/youzum.net\/fr\/category\/ai-club\/\" rel=\"category tag\">AI<\/a> <a href=\"https:\/\/youzum.net\/fr\/category\/committee\/\" rel=\"category tag\">Committee<\/a> <a href=\"https:\/\/youzum.net\/fr\/category\/news\/\" rel=\"category tag\">News<\/a> <a href=\"https:\/\/youzum.net\/fr\/category\/uncategorized\/\" rel=\"category tag\">Uncategorized<\/a>","rttpg_excerpt":"arXiv:2601.03273v2 Announce Type: replace Abstract: As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholding appropriate censorship boundaries has never been greater. While existing LLMs can detect dangerous or unsafe content, they often struggle with nuanced cases such\u2026","_links":{"self":[{"href":"https:\/\/youzum.net\/fr\/wp-json\/wp\/v2\/posts\/78436","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/youzum.net\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/youzum.net\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/youzum.net\/fr\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/youzum.net\/fr\/wp-json\/wp\/v2\/comments?post=78436"}],"version-history":[{"count":0,"href":"https:\/\/youzum.net\/fr\/wp-json\/wp\/v2\/posts\/78436\/revisions"}],"wp:attachment":[{"href":"https:\/\/youzum.net\/fr\/wp-json\/wp\/v2\/media?parent=78436"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/youzum.net\/fr\/wp-json\/wp\/v2\/categories?post=78436"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/youzum.net\/fr\/wp-json\/wp\/v2\/tags?post=78436"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}