--- title: Introducing Lamini Memory Tuning: 95% LLM Accuracy, 10x... description: Introducing Lamini Memory Tuning, a new approach to embedding facts into LLMs that improves factual accuracy and reduces hallucinations. Lamini Memory Tuning... canonical: https://daily.dev/posts/introducing-lamini-memory-tuning-95-llm-accuracy-10x-fewer-hallucinations-u4c12aa1h twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing Lamini Memory Tuning: 95% LLM Accuracy, 10x Fewer Hallucinations | daily.dev og:description: Introducing Lamini Memory Tuning, a new approach to embedding facts into LLMs that improves factual accuracy and reduces hallucinations. Lamini Memory Tuning... og:url: https://daily.dev/posts/introducing-lamini-memory-tuning-95-llm-accuracy-10x-fewer-hallucinations-u4c12aa1h og:image: https://api.daily.dev/og/posts/u4C12aA1H.png og:image:alt: Introducing Lamini Memory Tuning: 95% LLM Accuracy, 10x Fewer Hallucinations 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. # Introducing Lamini Memory Tuning: 95% LLM Accuracy, 10x Fewer Hallucinations **[Hacker News](https://daily.dev/sources/hn)** · 7 min read · 43 upvotes · 1 comments ## Summary Introducing Lamini Memory Tuning, a new approach to embedding facts into LLMs that improves factual accuracy and reduces hallucinations. Lamini Memory Tuning achieves 95% accuracy compared to 50% with other approaches, and reduces hallucinations from 50% to 5%. It overcomes the challenge of achieving precise factual accuracy while maintaining generalization capabilities. The method involves tuning millions of expert adapters with precise facts on top of open-source LLMs, resulting in high accuracy, high speed, and low cost. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community discussion Top comments from developers on daily.dev. **@mattybilly** · 2 upvotes > I would love to see this implemented and open-sourced. Imagine being able to see some ablation studies like removing some of the roughly ~1 million experts their setup uses and seeing how that affects memory. Or maybe see how the logprobs change for both memory based facts and creative reasoning problems as the number of experts increases/decreases. ## 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: [#ai](https://daily.dev/tags/ai), [#llm](https://daily.dev/tags/llm) [View this post on daily.dev](https://daily.dev/posts/introducing-lamini-memory-tuning-95-llm-accuracy-10x-fewer-hallucinations-u4c12aa1h) ```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":"Introducing Lamini Memory Tuning: 95% LLM Accuracy, 10x Fewer Hallucinations","url":"https://daily.dev/posts/introducing-lamini-memory-tuning-95-llm-accuracy-10x-fewer-hallucinations-u4c12aa1h","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-lamini-memory-tuning-95-llm-accuracy-10x-fewer-hallucinations-u4c12aa1h"},"datePublished":"2024-06-14T03:46:17.059Z","dateModified":"2024-08-23T15:08:07.553Z","description":"Introducing Lamini Memory Tuning, a new approach to embedding facts into LLMs that improves factual accuracy and reduces hallucinations. Lamini Memory Tuning...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6c40ce3fcb9c670c81fe388aa265ad6c?_a=AQAEuiZ","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6c40ce3fcb9c670c81fe388aa265ad6c?_a=AQAEuiZ","isAccessibleForFree":true,"articleSection":"Hacker News","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":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/introducing-lamini-memory-tuning-95-llm-accuracy-10x-fewer-hallucinations-u4c12aa1h","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":43},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"ai,llm","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Introducing Lamini Memory Tuning: 95% LLM Accuracy, 10x Fewer Hallucinations"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/introducing-lamini-memory-tuning-95-llm-accuracy-10x-fewer-hallucinations-u4c12aa1h","comment":[{"@type":"Comment","text":"I would love to see this implemented and open-sourced. Imagine being able to see some ablation studies like removing some of the roughly ~1 million experts their setup uses and seeing how that affects memory. Or maybe see how the logprobs change for both memory based facts and creative reasoning problems as the number of experts increases/decreases.","datePublished":"2024-06-17T20:31:36.122Z","url":"https://daily.dev/posts/u4C12aA1H#c-auoKbzVeO","author":{"@type":"Person","name":"Matt","url":"https://daily.dev/mattybilly","image":"https://lh3.googleusercontent.com/a/ACg8ocKpfkeNYEYvY717n_imoekLDxdYskvgQrGF42j66OLwyXJDkQ=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2}}]} ```