--- title: The Instruction Hierarchy: Training LLMs to Prioritize... description: The paper discusses training Language Model Manners (LLMs) to prioritize privileged instructions and proposes a hierarchy for models to consider conflict or... canonical: https://daily.dev/posts/the-instruction-hierarchy-training-llms-to-prioritize-privileged-instructions-c8dcotuxi twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions | daily.dev og:description: The paper discusses training Language Model Manners (LLMs) to prioritize privileged instructions and proposes a hierarchy for models to consider conflict or... og:url: https://daily.dev/posts/the-instruction-hierarchy-training-llms-to-prioritize-privileged-instructions-c8dcotuxi og:image: https://api.daily.dev/og/posts/c8dcOTUxi.png og:image:alt: The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions **[Simon Willison](https://daily.dev/sources/simonwillison)** · 1 min read · 0 upvotes · 0 comments ## Summary The paper discusses training Language Model Manners (LLMs) to prioritize privileged instructions and proposes a hierarchy for models to consider conflict or alignment with higher-level instructions. The authors claim improved performance against prompt injection benchmarks but acknowledge vulnerability to powerful adversarial attacks. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Don’t just attend KubeCon \+ CloudNativeCon, Merge Forward your experience\!](https://daily.dev/posts/don-t-just-attend-kubecon-cloudnativecon-merge-forward-your-experience--l0rpp73x8) · CNCF · 1 upvotes · 0 comments - [Announcing H2 2026 KCDs](https://daily.dev/posts/announcing-h2-2026-kcds-m96goajm1) · CNCF · 1 upvotes · 0 comments - [Two months of Open Community Groups](https://daily.dev/posts/two-months-of-open-community-groups-asf52zhbs) · CNCF · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#openai](https://daily.dev/tags/openai), [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/the-instruction-hierarchy-training-llms-to-prioritize-privileged-instructions-c8dcotuxi) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","url":"https://daily.dev/posts/the-instruction-hierarchy-training-llms-to-prioritize-privileged-instructions-c8dcotuxi","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-instruction-hierarchy-training-llms-to-prioritize-privileged-instructions-c8dcotuxi"},"datePublished":"2024-04-23T03:44:23.553Z","dateModified":"2025-07-28T02:21:14.534Z","description":"The paper discusses training Language Model Manners (LLMs) to prioritize privileged instructions and proposes a hierarchy for models to consider conflict or...","image":"https://media.daily.dev/image/upload/s--58gMhC4P--/f_auto/v1722860399/public/Placeholder%2012","thumbnailUrl":"https://media.daily.dev/image/upload/s--58gMhC4P--/f_auto/v1722860399/public/Placeholder%2012","isAccessibleForFree":true,"articleSection":"Simon Willison","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Simon Willison","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/cf12b897300740218b35f49a6309ec5b","url":"https://daily.dev/sources/simonwillison"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-instruction-hierarchy-training-llms-to-prioritize-privileged-instructions-c8dcotuxi","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,openai,prompt-injection","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Simon Willison","item":"https://daily.dev/sources/simonwillison"},{"@type":"ListItem","position":3,"name":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions"}]} ```