[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-334790-105":53,"doc-detail-334790-en":126},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","better-bill-gpt-comparing-large-language-models-against-legal-invoice-reviewers-abstract","Better Bill GPT - Comparing Large Language Models against Legal Invoice Reviewers - Abstract","","Legal invoice review is a costly, inconsistent, and time-consuming activity traditionally carried out by legal operations teams, lawyers, or billing specialists reviewing billing compliance line by line. This study performs the first empirical comparison of large language models (LLMs) versus human invoice reviewers—early-career lawyers, experienced lawyers, and legal operations professionals—evaluating accuracy, speed, and cost-effectiveness using expert ground truth. Results show LLMs outperform humans on all metrics, reaching up to 92% invoice decision accuracy and drastically reducing review time and cost.",{"@graph":63,"@context":118},[64,80,101],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":11,"@type":70,"position":76},"https://docshare.wps.com/template/presentations/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/better-bill-gpt-comparing-large-language-models-against-legal-invoice-reviewers-abstract/334790/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/better-bill-gpt-comparing-large-language-models-against-legal-invoice-reviewers-abstract/334790.png","ImageObject",442,249,{"name":88,"@type":89},"Oliver Hayes","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-27","2026-09-21",true,{"@type":98,"interactionType":99,"userInteractionCount":8},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"What does the study compare regarding legal invoice review?","Question",{"text":108,"@type":109},"It compares large language models against human invoice reviewers, including accuracy, speed, and cost-effectiveness.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"How accurate are LLMs compared with experienced lawyers in invoice approval decisions?",{"text":113,"@type":109},"LLMs reach up to 92% accuracy, surpassing experienced lawyers, which are described as capped at 72%.",{"name":115,"@type":106,"acceptedAnswer":116},"What are the study’s main speed and cost findings?",{"text":117,"@type":109},"LLM reviews can take as little as 3.6 seconds, while lawyers take 194 to 316 seconds per invoice; review expenses are reduced by 99.97%, dropping from about $4.27 per invoice to mere cents.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},334790,1791342240,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":8,"category_name":11,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":8,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":35,"language":135,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":136,"faqs":137,"seo_title":138,"seo_description":61,"update_tm":139,"read_time":140},687207020761,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","arXiv :2504 .0288 1v 1 [ cs .CL] 2 Apr 2025  \nBetter Bill GPT: Comparing Large Language Models against Legal Invoice Reviewers  \nNICK WHITEHOUSE, NICOLE LINCOLN, STEPHANIE YIU, LIZZIE CATTERSON, RIVINDU PERERA, AI Center of Excellence, Onit Inc, New Zealand  \nLegal invoice review is a costly, inconsistent, and time-consuming process, traditionally performed by Legal Operations, Lawyers or Billing Specialists who scrutinise billing compliance line by line. This study presents the first empirical comparison of Large Language Models (LLMs) against human invoice reviewers —Early-Career Lawyers, Experienced Lawyers, and Legal Operations Professionals—assessing their accuracy, speed, and cost-effectiveness. Benchmarking state-of-the-art LLMs against a ground truth set by expert legal professionals, our empirically substantiated findings reveal that LLMs decisively outperform humans across every metric. In invoice approval decisions, LLMs achieve up to 92% accuracy, surpassing the 72% ceiling set by experienced lawyers. On a granular level, LLMs dominate line-item classification, with top models reaching F-scores of 81%, compared to just 43% for the best-performing human group. Speed comparisons are even more striking — while lawyers take 194 to 316 seconds per invoice, LLMs are capable of completing reviews in as fast as 3.6 seconds. And cost? AI slashes review expenses by 99.97%, reducing invoice processing costs from an average of $4.27 per invoice for human invoice reviewers to mere cents. These results highlight the evolving role of AI in legal spend management. As law firms and corporate legal departments struggle with inefficiencies, this study signals a seismic shift: The era ofLLM-powered legal spend management is not on the horizon, it has arrived. The challenge ahead is not whether AI can perform as well as human reviewers, but how legal teams will strategically incorporate it, balancing automation with human discretion.  \nCCS Concepts: • Computing methodologies → Natural language generation; Information extraction; • Applied computing → Law; Document searching.  \nAdditional Key Words and Phrases: Generative AI, Large Language Models, Spend Management, Enterprise Legal Management, Invoice Review  \nACM Reference Format:  \nNick Whitehouse, Nicole Lincoln, Stephanie Yiu, Lizzie Catterson, Rivindu Perera. 2025. Better Bill GPT: Comparing Large Language  \nModels against Legal Invoice Reviewers. 1, 1 (April 2025), 17 pages. [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \n1 Introduction  \nOur previous study, Better Call GPT [6], demonstrated that Large Language Models (LLMs) [8] can achieve humancomparable accuracy in contract review tasks while significantly reducing time and costs. By establishing a foundational benchmark for the evaluation of legal context, the aforementioned research highlighted the potential for LLMs to improve efficiency in contract review. Building on these findings, the present study examines the application of LLMs in  \nAuthor’s Contact Information: Nick Whitehouse, Nicole Lincoln, Stephanie Yiu, Lizzie Catterson, Rivindu Perera, [nick.whitehouse@onit.com](nick.whitehouse@onit.com), AI Center of Excellence, Onit Inc, Aukland, New Zealand.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyright for this work is held by Onit Inc., and all rights are reserved. Abstracting with credit is permitted. To copy otherwise, republish, post on servers, or redistribute to lists requires prior written permission from Onit Inc.  \n© 2025 Copyright held by Onit Inc. Publication rights licensed to Onit Inc..  \n2 Whitehouse et al.  \nlegal invoice processing, investigating their ability to match or surpass human expertise in identifying non-compliant line items, enforcin","cbCaiamv0zbNands","https://ap.wps.com/l/cbCaiamv0zbNands","pdf",730681,"English","# Introduction\n## Research questions\n## Invoice processing context","[{\"question\":\"What does the study compare regarding legal invoice review?\",\"answer\":\"It compares large language models against human invoice reviewers, including accuracy, speed, and cost-effectiveness.\"},{\"question\":\"How accurate are LLMs compared with experienced lawyers in invoice approval decisions?\",\"answer\":\"LLMs reach up to 92% accuracy, surpassing experienced lawyers, which are described as capped at 72%.\"},{\"question\":\"What are the study’s main speed and cost findings?\",\"answer\":\"LLM reviews can take as little as 3.6 seconds, while lawyers take 194 to 316 seconds per invoice; review expenses are reduced by 99.97%, dropping from about $4.27 per invoice to mere cents.\"}]","Better Bill GPT - Comparing Large Language Models against Legal Invoice Reviewers - Abstract | PDF",1790008386,6]