[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82601-en":3,"doc-seo-82601-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82601,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","AI Assistance for Human Review of Default Judgments","Overwhelmed courts in the United States review millions of default judgments each year, and manual auditing is slow and error-prone. An audit of 188 Los Angeles Superior Court debt-collection cases finds 4% with major defects, 10% with inconsistencies requiring reduced judgments, and 32% with errors requiring amendments. The Default Assistant uses large language models to check predetermined legal requirements and returns cited, quote-and-table grounded recommendations for expert review. A controlled study with 66 law students shows higher accuracy ( +6.0%) and faster review (+25.9%), with larger gains for document-intensive statutory checks.","AI Assistance for Human Review of Default Judgments  \nTheodora Worledge 1 * , Othman Bensouda Koraichi2 , Daniel Bernal2 , Aviv Caspi2,3 , Tatsunori Hashimoto 1 , Carlos Guestrin 1 , David Freeman Engstrom2,4  \n1 Stanford Computer Science, Stanford University  \n2Deborah L. Rhode Center, Stanford Law School  \n3University of Chicago Law School  \n4 Stanford Law School  \narXiv :2607 .0 1256v 1 [ cs .CY] 4 Jun 2026  \nAbstract  \nOverwhelmed courts in the United States review millions of default judgments each year. Unfortunately, such manual reviews are time-consuming and prone to error. In an audit of 188 debt collection cases granted default judgment by the Superior Court of Los Angeles, we find that 4% contained major defects that should have entirely prevented default judgment, 10% contained inconsistencies requiring reduced judgments, and 32% contained errors requiring amendment prior to judgment. To support courthouses in default judgment review, we collaborated with courthouse attorneys and judges in designing a Default Assistant. The Default Assistant employs large language models to evaluate a case with respect to predetermined legal requirements and provide cited recommendations for an expert user’s review. We equip users to verify these recommendations by grounding the assistant’s explanationsin cited quotes and tables from the original case filings. We conduct a controlled study with 66 law students that conservatively simulates court review, with more time and resources than court staff. We nevertheless find users aided by the Default Assistant were 6.0% more accurate on the average requirement than unaided reviewers (p \u003C 1.0e-4) . Simultaneously, users were 25.9% faster in reviewing the average requirement than unaided reviewers (p \u003C 2.5e-10) . Statutory requirements demanding extensive document search realized the largest gains, with error reductions and time savings from AI assistance up to 62% and 34%, respectively, relative to unassisted user performance and with differences statistically significant (p \u003C 0.05) . Our work provides a proof-of-concept that AI assistants with citations have the potential to help resource-constrained courts conduct default judgment review more accurately and efficiently.  \nIntroduction  \nThe American civil justice system is failing to meet the needs of millions of litigants. Many of the 15 million civil cases filed in American state courts each year represent personal crises—a debt collection that results in wage garnishment, an eviction that leads to homelessness (Johnson Raba 2023; Garnham, Gershenson, and Desmond 2022)—that fuel cycles of unemployment, poverty, poor health, and family breakdown (Mullen 2019; Desmond and Kimbro 2015) . Yet, despite these high stakes, roughly three-quarters of  \n* [Corresponding author: worledge@stanford.edu](Corresponding author: worledge@stanford.edu)  \nthese civil cases involve at least one person who cannot afford a lawyer (Agor, Graves, and Miller 2015) . Many defendants do not take action to defend themselves in court; defendants only respond in 6% of debt collection cases filed atthe Superior Court of Los Angeles County (SCLAC) (Johnson Raba 2023) . With minimal adversarial process to surface evidence of defects in cases, courts, constrained by the impracticality of rigorous manual review, are more likely to issue erroneous default judgments (Jimnez 2015; Bookman 2024) .  \nThe court caseload for default judgment review is crushing. Each year, SCLAC—the largest trial court in the nation 1—routes as many as 30,000 debt collection default judgment requests to court staff for manual review. The high caseload creates severe time constraints. SCLAC research attorneys spend on average four minutes per case to verify over a dozen statutory requirements.2 The failure of any requirement influences the judge’s decision to grant default judgment in favor of debt buyers pursuant to CA Civil Code §§ 1788 .58-60. Given such resource constraints, even the most","cbCaiv7Z2emiuIpF","https://ap.wps.com/l/cbCaiv7Z2emiuIpF","pdf",2927067,1,15,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What problem does the paper address in default judgment review?\",\"answer\":\"The paper addresses the burden on courts reviewing millions of default judgments, where manual review is time-consuming and prone to errors.\"},{\"question\":\"What defects were found in the audited default-judgment cases?\",\"answer\":\"In 188 Los Angeles Superior Court debt-collection cases, 4% contained major defects that should have prevented default judgment, 10% had inconsistencies requiring reduced judgments, and 32% had errors requiring amendments before judgment.\"},{\"question\":\"How does the Default Assistant support expert review, and what were the study results?\",\"answer\":\"The Default Assistant uses large language models to evaluate cases against predetermined legal requirements and provides cited recommendations grounded in quotes and tables from the filings. In a study simulating court review, assisted users were 6.0% more accurate and 25.9% faster overall, with larger improvements for document-search-heavy statutory requirements.\"}]",1784181729,38,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"ai-assistance-for-human-review-of-default-judgments","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/ai-assistance-for-human-review-of-default-judgments/82601/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in default judgment review?","Question",{"text":75,"@type":76},"The paper addresses the burden on courts reviewing millions of default judgments, where manual review is time-consuming and prone to errors.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What defects were found in the audited default-judgment cases?",{"text":80,"@type":76},"In 188 Los Angeles Superior Court debt-collection cases, 4% contained major defects that should have prevented default judgment, 10% had inconsistencies requiring reduced judgments, and 32% had errors requiring amendments before judgment.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the Default Assistant support expert review, and what were the study results?",{"text":84,"@type":76},"The Default Assistant uses large language models to evaluate cases against predetermined legal requirements and provides cited recommendations grounded in quotes and tables from the filings. In a study simulating court review, assisted users were 6.0% more accurate and 25.9% faster overall, with larger improvements for document-search-heavy statutory requirements.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]