{"id":47505,"date":"2025-10-28T07:44:18","date_gmt":"2025-10-28T07:44:18","guid":{"rendered":"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/"},"modified":"2025-10-28T07:44:18","modified_gmt":"2025-10-28T07:44:18","slug":"isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models","status":"publish","type":"post","link":"https:\/\/youzum.net\/zh\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/","title":{"rendered":"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models"},"content":{"rendered":"<p>arXiv:2510.23558v1 Announce Type: cross<br \/>\nAbstract: Large Audio Language Models (LALMs), which couple acoustic perception with large language models (LLMs) to extract and understand diverse information from audio, have attracted intense interest from both academic and industrial communities. However, existing LALMs are highly sensitive to how instructions are phrased, affecting both (i) instruction-following rates and (ii) task performance. Yet, no existing benchmarks offer a systematic and comprehensive evaluation of this sensitivity. We introduce ISA-Bench, a dynamic benchmark evaluating instruction sensitivity for LALMs along three axes: instruction description, output format, and task composition. We assess recent open-source and proprietary LALMs using ISA-Bench, profiling both compliance and accuracy under controlled instruction variations. Experimental results reveal that even state-of-the-art LALMs suffer significant instruction sensitivity, leading to degraded performance on fundamental audio understanding tasks. To mitigate this issue, we fine-tune Qwen2-Audio on a specifically constructed complex instruction-variant dataset, achieving a marked improvement in instruction-following performance. However, this also induces nontrivial catastrophic forgetting: the model loses some previously mastered task capabilities when exposed to new instruction styles. Our benchmark provides a standardized basis for assessing and improving instruction sensitivity in LALMs, underscoring the need for instruction-robust audio understanding in real-world pipelines.<\/p>","protected":false},"excerpt":{"rendered":"<p>arXiv:2510.23558v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs), which couple acoustic perception with large language models (LLMs) to extract and understand diverse information from audio, have attracted intense interest from both academic and industrial communities. However, existing LALMs are highly sensitive to how instructions are phrased, affecting both (i) instruction-following rates and (ii) task performance. Yet, no existing benchmarks offer a systematic and comprehensive evaluation of this sensitivity. We introduce ISA-Bench, a dynamic benchmark evaluating instruction sensitivity for LALMs along three axes: instruction description, output format, and task composition. We assess recent open-source and proprietary LALMs using ISA-Bench, profiling both compliance and accuracy under controlled instruction variations. Experimental results reveal that even state-of-the-art LALMs suffer significant instruction sensitivity, leading to degraded performance on fundamental audio understanding tasks. To mitigate this issue, we fine-tune Qwen2-Audio on a specifically constructed complex instruction-variant dataset, achieving a marked improvement in instruction-following performance. However, this also induces nontrivial catastrophic forgetting: the model loses some previously mastered task capabilities when exposed to new instruction styles. Our benchmark provides a standardized basis for assessing and improving instruction sensitivity in LALMs, underscoring the need for instruction-robust audio understanding in real-world pipelines.<\/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-47505","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>ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models - 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\/zh\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models - 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\/zh\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/\" \/>\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=\"2025-10-28T07:44:18+00:00\" \/>\n<meta name=\"author\" content=\"admin NU\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin NU\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/\"},\"author\":{\"name\":\"admin NU\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c\"},\"headline\":\"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models\",\"datePublished\":\"2025-10-28T07:44:18+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/\"},\"wordCount\":206,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#organization\"},\"articleSection\":[\"AI\",\"Committee\",\"News\",\"Uncategorized\"],\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/\",\"url\":\"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/\",\"name\":\"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models - YouZum\",\"isPartOf\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#website\"},\"datePublished\":\"2025-10-28T07:44:18+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\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/youzum.net\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models\"}]},{\"@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\":\"zh-Hans\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/yousum.gpucore.co\/#organization\",\"name\":\"Drone Association Thailand\",\"url\":\"https:\/\/yousum.gpucore.co\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@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\":\"zh-Hans\",\"@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\/zh\/members\/adminnu\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models - 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\/zh\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/","og_locale":"zh_CN","og_type":"article","og_title":"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models - 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\/zh\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/","og_site_name":"YouZum","article_publisher":"https:\/\/www.facebook.com\/DroneAssociationTH\/","article_published_time":"2025-10-28T07:44:18+00:00","author":"admin NU","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin NU","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"1 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/#article","isPartOf":{"@id":"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/"},"author":{"name":"admin NU","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c"},"headline":"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models","datePublished":"2025-10-28T07:44:18+00:00","mainEntityOfPage":{"@id":"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/"},"wordCount":206,"commentCount":0,"publisher":{"@id":"https:\/\/yousum.gpucore.co\/#organization"},"articleSection":["AI","Committee","News","Uncategorized"],"inLanguage":"zh-Hans","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/","url":"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/","name":"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models - YouZum","isPartOf":{"@id":"https:\/\/yousum.gpucore.co\/#website"},"datePublished":"2025-10-28T07:44:18+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\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/youzum.net\/isa-bench-benchmarking-instruction-sensitivity-for-large-audio-language-models\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/youzum.net\/"},{"@type":"ListItem","position":2,"name":"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models"}]},{"@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":"zh-Hans"},{"@type":"Organization","@id":"https:\/\/yousum.gpucore.co\/#organization","name":"Drone Association Thailand","url":"https:\/\/yousum.gpucore.co\/","logo":{"@type":"ImageObject","inLanguage":"zh-Hans","@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":"zh-Hans","@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\/zh\/members\/adminnu\/"}]}},"rttpg_featured_image_url":null,"rttpg_author":{"display_name":"admin NU","author_link":"https:\/\/youzum.net\/zh\/members\/adminnu\/"},"rttpg_comment":0,"rttpg_category":"<a href=\"https:\/\/youzum.net\/zh\/category\/ai-club\/\" rel=\"category tag\">AI<\/a> <a href=\"https:\/\/youzum.net\/zh\/category\/committee\/\" rel=\"category tag\">Committee<\/a> <a href=\"https:\/\/youzum.net\/zh\/category\/news\/\" rel=\"category tag\">News<\/a> <a href=\"https:\/\/youzum.net\/zh\/category\/uncategorized\/\" rel=\"category tag\">Uncategorized<\/a>","rttpg_excerpt":"arXiv:2510.23558v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs), which couple acoustic perception with large language models (LLMs) to extract and understand diverse information from audio, have attracted intense interest from both academic and industrial communities. However, existing LALMs are highly sensitive to how instructions are phrased, affecting both (i) instruction-following rates and (ii)&hellip;","_links":{"self":[{"href":"https:\/\/youzum.net\/zh\/wp-json\/wp\/v2\/posts\/47505","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/youzum.net\/zh\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/youzum.net\/zh\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/youzum.net\/zh\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/youzum.net\/zh\/wp-json\/wp\/v2\/comments?post=47505"}],"version-history":[{"count":0,"href":"https:\/\/youzum.net\/zh\/wp-json\/wp\/v2\/posts\/47505\/revisions"}],"wp:attachment":[{"href":"https:\/\/youzum.net\/zh\/wp-json\/wp\/v2\/media?parent=47505"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/youzum.net\/zh\/wp-json\/wp\/v2\/categories?post=47505"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/youzum.net\/zh\/wp-json\/wp\/v2\/tags?post=47505"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}