{"id":15700,"date":"2024-07-16T10:01:24","date_gmt":"2024-07-16T02:01:24","guid":{"rendered":"https:\/\/www.1ai.net\/?p=15700"},"modified":"2024-07-16T10:01:24","modified_gmt":"2024-07-16T02:01:24","slug":"%e5%be%ae%e8%bd%af%e4%b8%ba-excel-%e7%ad%89%e7%a0%94%e5%8f%91%e6%96%b0-ai-%e6%a8%a1%e5%9e%8b%ef%bc%9a%e6%80%a7%e8%83%bd%e8%be%83%e5%b8%b8%e8%a7%84%e6%96%b9%e6%a1%88%e6%8f%90%e9%ab%98-25-6%ef%bc%8c","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/15700.html","title":{"rendered":"Microsoft develops new AI model for Excel and other applications: performance is 25.6% higher than conventional solutions, and word usage cost is reduced by 96%"},"content":{"rendered":"<p>according to<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%be%ae%e8%bd%af\" title=\"[View articles tagged with [Microsoft]]\" target=\"_blank\" >Microsoft<\/a>The latest research paper is planned to be <a href=\"https:\/\/www.1ai.net\/en\/tag\/excel\" title=\"[See articles with [Excel] label]\" target=\"_blank\" >Excel<\/a>, Google Sheets and other spreadsheet applications to develop new AI <a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%a4%a7%e8%af%ad%e8%a8%80%e6%a8%a1%e5%9e%8b\" title=\"[View articles tagged with [large language model]]\" target=\"_blank\" >Large Language Model<\/a>&#8212;<a href=\"https:\/\/www.1ai.net\/en\/tag\/spreadsheetllm\" title=\"[See article with [SpraadsheetLLM] label]\" target=\"_blank\" >SpreadsheetLLM<\/a>.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-15701\" title=\"1fe2a5e9-a6db-431d-936c-136ef8bf1b45\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/1fe2a5e9-a6db-431d-936c-136ef8bf1b45.jpg\" alt=\"1fe2a5e9-a6db-431d-936c-136ef8bf1b45\" width=\"760\" height=\"518\" \/><\/p>\n<p>Researchers say that existing spreadsheet applications are rich in functionality and provide users with a large number of options in terms of layout and formatting, so traditional AI large language models are difficult to cope with spreadsheet processing scenarios.<\/p>\n<p>SpreadsheetLLM is an AI model designed specifically for spreadsheet applications. Microsoft has also developed SheetCompressor (compressed spreadsheet) to enable SpreadsheetLLM to better understand and process spreadsheet data.<\/p>\n<p>According to the abstract of the paper, the SpreadsheetLLM model mainly consists of three modules: compression based on structural anchors, reverse index transformation, and data format-aware aggregation.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-15702\" title=\"abfb5710-c5a7-4909-8428-d6d6530acef5.jpg@s_2w_820h_363\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/abfb5710-c5a7-4909-8428-d6d6530acef5.jpg@s_2w_820h_363.jpg\" alt=\"abfb5710-c5a7-4909-8428-d6d6530acef5.jpg@s_2w_820h_363\" width=\"820\" height=\"363\" \/><\/p>\n<p>SpreadsheetLLM significantly improves the performance of the spreadsheet table detection task, outperforming the general method by 25.6% in the contextual learning setting of GPT4; using tokens reduces the cost by 96% and provides better processing results.<\/p>\n<p>There is no news yet on when or if Microsoft plans to make SpreadsheetLLM available to the public. The paper notes that the model still has some limitations, and cannot efficiently handle spreadsheets that use background colors and borders; SheetCompressor cannot currently compress cells containing natural language, etc.<\/p>","protected":false},"excerpt":{"rendered":"<p>Based on Microsoft's latest published research paper, it is planned to develop a new AI Large Language Model - SpreadsheetLM for spreadsheet applications such as Excel, Google Sheets. The researchers indicated that the existing spreadsheet applications are very functional and provide users with a large number of options in layout and format, making the traditional AI large language model difficult to handle. And SpreadsheetLLM, an AI model designed specifically for spreadsheet applications, Microsoft also developed SheetCompressor, which allows SpreadsheetLLM to better understand and process spreadsheet data. Reference papers<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[1498,3522,706,280],"collection":[],"class_list":["post-15700","post","type-post","status-publish","format-standard","hentry","category-news","tag-excel","tag-spreadsheetllm","tag-706","tag-280"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/15700","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=15700"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/15700\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=15700"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=15700"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=15700"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=15700"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}