{"id":23204,"date":"2025-04-30T10:08:11","date_gmt":"2025-04-30T10:08:11","guid":{"rendered":"https:\/\/www.imprima.com\/?p=23204"},"modified":"2025-05-01T11:28:12","modified_gmt":"2025-05-01T11:28:12","slug":"not-all-ai-created-equal","status":"publish","type":"post","link":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal","title":{"rendered":"Not all AI is created equal \u2013 The benefits of Large Language Models for Redaction"},"content":{"rendered":"\n<p>Over the last few weeks, we\u2019ve discussed the importance of the <a href=\"https:\/\/www.imprima.com\/blog\/the-most-secure-redaction-method\" target=\"_blank\" rel=\"noreferrer noopener\">secure application of redaction<\/a> and how failure to to do so can lead to some <a href=\"https:\/\/www.imprima.com\/blog\/how-to-avoid-redaction-fails\" target=\"_blank\" rel=\"noreferrer noopener\">embarrassing oversights<\/a>. This week, we\u2019re diving into how artificial intelligence (AI) can actually <em>find<\/em> the text to be redacted &#8211; but not just any AI. Let\u2019s unpack this.<\/p>\n\n\n\n<div style=\"height:42px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><Span style=\"font-weight:800\">The Power of Machine Learning and Large Language Models<\/span><\/p>\n\n\n\n<p>Not all AI is created equal. Some might call regex a form of AI, but it has serious limitations for redaction. Whilst regex and search techniques do have their place (see our previous blog on <a href=\"https:\/\/www.imprima.com\/blog\/the-best-approach-to-ai-redaction\" target=\"_blank\" rel=\"noreferrer noopener\">The Best Approach to AI Redaction<\/a>) for reliable, accurate results, we turn to machine learning, specifically a cutting-edge approach called Large Language Models (LLMs) &#8211; the same technology behind tools like ChatGPT.<\/p>\n\n\n\n<div style=\"height:42px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><Span style=\"font-weight:800\">What Exactly Is a Large Language Model?<\/span><\/p>\n\n\n\n<p>Think of an LLM as a super-smart <a href=\"https:\/\/en.wikipedia.org\/wiki\/Neural_network\" target=\"_blank\" rel=\"noreferrer noopener\">neural network<\/a> trained on massive amounts of text, like Wikipedia or public web data. Its job? To predict the next word in a sentence (or fill in missing words) based on the surrounding context. It\u2019s like training for a \u201cfill-in-the-blank\u201d test, such as completing the phrase \u201cmonkeys like to ___ bananas.\u201d LLMs are designed to ace this!<\/p>\n\n\n\n<p>Through this training, LLMs learn the patterns of language, grammar, style, and even meaning. This is why ChatGPT can sound so eloquent and informative (though it\u2019s not always 100% accurate &#8211; check out this article for a fun take: <a href=\"https:\/\/medium.com\/@konstantine_45825\/chatgpt-is-no-stochastic-parrot-but-it-also-claims-that-1-is-greater-than-1-e3cd1fc303e0\" target=\"_blank\" rel=\"noreferrer noopener\">ChatGPT Is No Stochastic Parrot, But It Thinks 1 Is Greater Than 1<\/a>). Best of all, LLMs don\u2019t need humans to manually label their training data, which means they can learn from vast datasets with minimal human effort (just some brilliant data scientists and powerful computers!).<\/p>\n\n\n\n<div style=\"height:42px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><Span style=\"font-weight:800\">How Imprima Uses LLMs for Redaction<\/span><\/p>\n\n\n\n<p>At Imprima, we\u2019ve tailored an LLM specifically for redaction, training it on the types of documents commonly found in due diligence. Because we use LLMs, our technology works across multiple languages, using data from one language to boost accuracy in others. Instead of searching for exact words or phrases like traditional methods, the LLM understands the context and meaning of the text. This allows it to identify and redact sensitive information with far greater precision.<\/p>\n\n\n\n<p>The result? Unmatched accuracy and reliability that blows other automated redaction tools out of the water. We\u2019ve demonstrated this in a previous post (<a href=\"https:\/\/www.imprima.com\/blog\/smart-vdrs-accuracy\" target=\"_blank\" rel=\"noreferrer noopener\">Smart VDRs: It\u2019s All About Accuracy<\/a>), and we\u2019ll dive deeper into the results next week.<\/p>\n\n\n\n<div style=\"height:42px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><Span style=\"font-weight:800\">Why This Matters for Due Diligence<\/span><\/p>\n\n\n\n<p>At Imprima, we believe LLMs can revolutionise due diligence. Beyond redaction, they can extract critical insights from documents (like our Smart Summaries tool) to streamline the DD process. Utilising AI in Due Diligence, allows users to gather information faster and have a \u201csecond pair of eyes\u201d so they can focus on what matters most. At Imprima we\u2019re focused on building trustworthy, reliable AI and its <a href=\"https:\/\/www.ey.com\/en_ch\/insights\/strategy-transactions\/how-ai-will-impact-due-diligence-in-m-and-a-transactions\" target=\"_blank\" rel=\"noreferrer noopener\">practical benefits for M&amp;A Due Diligence.<\/a><\/p>\n\n\n\n<div style=\"height:42px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><Span style=\"font-weight:800\">What\u2019s Next?<\/span><\/p>\n\n\n\n<p>Coming soon we&#8217;ll share real-world results from our LLM-based redaction tool, showing just how accurate and reliable it is when applied to actual DD data.<\/p>\n\n\n\n<p>Stay tuned!<\/p>\n\n\n\n<div style=\"height:42px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p><span style=\"font-weight:500\">Are you looking for a VDR with fully integrated redaction software which leverages AI? Speak to our <a href=\"https:\/\/www.imprima.com\/contact\/sales\/?productfeature=SMART%20REDACTION%20LLM\" target=\"_blank\" rel=\"noreferrer noopener\">sales team<\/a> or check out our <a href=\"https:\/\/www.imprima.com\/virtual-data-room\/smart-redaction\" target=\"_blank\" rel=\"noreferrer noopener\">Smart Redaction page here<\/a>.<\/span><\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Over the last few weeks, we\u2019ve discussed the importance of the secure application of redaction and how failure to to do so can lead to some embarrassing oversights. This week, we\u2019re diving into how artificial intelligence (AI) can actually find the text to be redacted &#8211; but not just any AI. Let\u2019s unpack this. The [&hellip;]<\/p>\n","protected":false},"author":8,"featured_media":23205,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[169,163,171],"tags":[],"class_list":["post-23204","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","category-ma","category-vdr"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v26.4 (Yoast SEO v26.4) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Not all AI is created equal \u2013 The benefits of Large Language Models for Redaction - Imprima<\/title>\n<meta name=\"description\" content=\"Read about how Large Language Models (LLMs) transform the process of redaction with unmatched accuracy and reliability.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Not all AI is created equal \u2013 The benefits of Large Language Models for Redaction\" \/>\n<meta property=\"og:description\" content=\"Read about how Large Language Models (LLMs) transform the process of redaction with unmatched accuracy and reliability.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal\" \/>\n<meta property=\"og:site_name\" content=\"Imprima\" \/>\n<meta property=\"article:published_time\" content=\"2025-04-30T10:08:11+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-05-01T11:28:12+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.imprima.com\/wp-content\/uploads\/2025\/04\/LLM-blog-feature1200.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"710\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Marcus Tolan\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Marcus Tolan\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal\"},\"author\":{\"name\":\"Marcus Tolan\",\"@id\":\"https:\/\/www.imprima.com\/#\/schema\/person\/91ac413cefc7cd6c4ec7034f7cef47f2\"},\"headline\":\"Not all AI is created equal \u2013 The benefits of Large Language Models for Redaction\",\"datePublished\":\"2025-04-30T10:08:11+00:00\",\"dateModified\":\"2025-05-01T11:28:12+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal\"},\"wordCount\":563,\"publisher\":{\"@id\":\"https:\/\/www.imprima.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.imprima.com\/wp-content\/uploads\/2025\/04\/LLM-blog-feature1200.jpg\",\"articleSection\":[\"Artificial Intelligence\",\"M&amp;A\",\"VDR\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal\",\"url\":\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal\",\"name\":\"Not all AI is created equal \u2013 The benefits of Large Language Models for Redaction - Imprima\",\"isPartOf\":{\"@id\":\"https:\/\/www.imprima.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.imprima.com\/wp-content\/uploads\/2025\/04\/LLM-blog-feature1200.jpg\",\"datePublished\":\"2025-04-30T10:08:11+00:00\",\"dateModified\":\"2025-05-01T11:28:12+00:00\",\"description\":\"Read about how Large Language Models (LLMs) transform the process of redaction with unmatched accuracy and reliability.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#primaryimage\",\"url\":\"https:\/\/www.imprima.com\/wp-content\/uploads\/2025\/04\/LLM-blog-feature1200.jpg\",\"contentUrl\":\"https:\/\/www.imprima.com\/wp-content\/uploads\/2025\/04\/LLM-blog-feature1200.jpg\",\"width\":1200,\"height\":710,\"caption\":\"Feature-image-LLM\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.imprima.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Not all AI is created equal \u2013 The benefits of Large Language Models for Redaction\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.imprima.com\/#website\",\"url\":\"https:\/\/www.imprima.com\/\",\"name\":\"Imprima\",\"description\":\"Secure Online Data Room Services by Imprima\",\"publisher\":{\"@id\":\"https:\/\/www.imprima.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.imprima.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.imprima.com\/#organization\",\"name\":\"Imprima\",\"url\":\"https:\/\/www.imprima.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.imprima.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.imprima.com\/wp-content\/uploads\/2021\/05\/imprima-logo-new.svg\",\"contentUrl\":\"https:\/\/www.imprima.com\/wp-content\/uploads\/2021\/05\/imprima-logo-new.svg\",\"width\":507.43,\"height\":149.18,\"caption\":\"Imprima\"},\"image\":{\"@id\":\"https:\/\/www.imprima.com\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.imprima.com\/#\/schema\/person\/91ac413cefc7cd6c4ec7034f7cef47f2\",\"name\":\"Marcus Tolan\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Not all AI is created equal \u2013 The benefits of Large Language Models for Redaction - Imprima","description":"Read about how Large Language Models (LLMs) transform the process of redaction with unmatched accuracy and reliability.","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:\/\/www.imprima.com\/blog\/not-all-ai-created-equal","og_locale":"en_US","og_type":"article","og_title":"Not all AI is created equal \u2013 The benefits of Large Language Models for Redaction","og_description":"Read about how Large Language Models (LLMs) transform the process of redaction with unmatched accuracy and reliability.","og_url":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal","og_site_name":"Imprima","article_published_time":"2025-04-30T10:08:11+00:00","article_modified_time":"2025-05-01T11:28:12+00:00","og_image":[{"width":1200,"height":710,"url":"https:\/\/www.imprima.com\/wp-content\/uploads\/2025\/04\/LLM-blog-feature1200.jpg","type":"image\/jpeg"}],"author":"Marcus Tolan","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Marcus Tolan","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#article","isPartOf":{"@id":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal"},"author":{"name":"Marcus Tolan","@id":"https:\/\/www.imprima.com\/#\/schema\/person\/91ac413cefc7cd6c4ec7034f7cef47f2"},"headline":"Not all AI is created equal \u2013 The benefits of Large Language Models for Redaction","datePublished":"2025-04-30T10:08:11+00:00","dateModified":"2025-05-01T11:28:12+00:00","mainEntityOfPage":{"@id":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal"},"wordCount":563,"publisher":{"@id":"https:\/\/www.imprima.com\/#organization"},"image":{"@id":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#primaryimage"},"thumbnailUrl":"https:\/\/www.imprima.com\/wp-content\/uploads\/2025\/04\/LLM-blog-feature1200.jpg","articleSection":["Artificial Intelligence","M&amp;A","VDR"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal","url":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal","name":"Not all AI is created equal \u2013 The benefits of Large Language Models for Redaction - Imprima","isPartOf":{"@id":"https:\/\/www.imprima.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#primaryimage"},"image":{"@id":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#primaryimage"},"thumbnailUrl":"https:\/\/www.imprima.com\/wp-content\/uploads\/2025\/04\/LLM-blog-feature1200.jpg","datePublished":"2025-04-30T10:08:11+00:00","dateModified":"2025-05-01T11:28:12+00:00","description":"Read about how Large Language Models (LLMs) transform the process of redaction with unmatched accuracy and reliability.","breadcrumb":{"@id":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#primaryimage","url":"https:\/\/www.imprima.com\/wp-content\/uploads\/2025\/04\/LLM-blog-feature1200.jpg","contentUrl":"https:\/\/www.imprima.com\/wp-content\/uploads\/2025\/04\/LLM-blog-feature1200.jpg","width":1200,"height":710,"caption":"Feature-image-LLM"},{"@type":"BreadcrumbList","@id":"https:\/\/www.imprima.com\/blog\/not-all-ai-created-equal#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.imprima.com\/"},{"@type":"ListItem","position":2,"name":"Not all AI is created equal \u2013 The benefits of Large Language Models for Redaction"}]},{"@type":"WebSite","@id":"https:\/\/www.imprima.com\/#website","url":"https:\/\/www.imprima.com\/","name":"Imprima","description":"Secure Online Data Room Services by Imprima","publisher":{"@id":"https:\/\/www.imprima.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.imprima.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.imprima.com\/#organization","name":"Imprima","url":"https:\/\/www.imprima.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.imprima.com\/#\/schema\/logo\/image\/","url":"https:\/\/www.imprima.com\/wp-content\/uploads\/2021\/05\/imprima-logo-new.svg","contentUrl":"https:\/\/www.imprima.com\/wp-content\/uploads\/2021\/05\/imprima-logo-new.svg","width":507.43,"height":149.18,"caption":"Imprima"},"image":{"@id":"https:\/\/www.imprima.com\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/www.imprima.com\/#\/schema\/person\/91ac413cefc7cd6c4ec7034f7cef47f2","name":"Marcus Tolan"}]}},"_links":{"self":[{"href":"https:\/\/www.imprima.com\/wp-json\/wp\/v2\/posts\/23204","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.imprima.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.imprima.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.imprima.com\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/www.imprima.com\/wp-json\/wp\/v2\/comments?post=23204"}],"version-history":[{"count":0,"href":"https:\/\/www.imprima.com\/wp-json\/wp\/v2\/posts\/23204\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.imprima.com\/wp-json\/wp\/v2\/media\/23205"}],"wp:attachment":[{"href":"https:\/\/www.imprima.com\/wp-json\/wp\/v2\/media?parent=23204"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.imprima.com\/wp-json\/wp\/v2\/categories?post=23204"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.imprima.com\/wp-json\/wp\/v2\/tags?post=23204"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}