[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81640-en":3,"doc-seo-81640-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},81640,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation","Systematic reviews require comprehensive evidence collection and synthesis across large document corpora to answer pre-specified research questions in domains such as finance, social sciences, and technical fields. Manual evidence-table construction is labor-intensive, while many LLM assistants using embedding or keyword retrieval fail to meet coverage and transparency needs. SLIDERS introduces an LLM-based pipeline that automatically assembles tailored evidence tables, extracts structured data and full-text excerpts, and uses an evidence reconciliation agent to reconcile conflicts via code and synthesize coherent results, with strong benchmark performance.","arXiv :2604 .22294v2 [ cs .CL] 9 Jul 2026  \nSLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation ∗  \nHarshit Joshi Priyank Shethia Jadelynn Dao Monica S. Lam  \nComputer Science Department, Stanford University {hj, [lam}@cs.stanford.edu](lam}@cs.stanford.edu)  \nAbstract  \nSystematic reviews – which requires comprehensive evidence collection and synthesis from large document corpora in response to targeted research questions – are foundational in finance, social sciences, and other technical fields. Manual construction of evidence tables is labor-intensive, and recent LLM-based assistants relying on embedding or keyword based search often fail to meet the coverage standards of systematic reviews. We introduce SLIDERS, a novel LLM-based methodology for systematic reviews, by automatically assembling evidence tables tailored to research questions. In addition to extracting structured data from documents, SLIDERS can extract full-text excerpts that serve as direct evidence or as provenance for structured data. Core to SLIDERS is an automated evidence reconciliation agent that writes code to analyze and reconcile extracted evidence, bringing together information fragmented across documents, resolving inconsistencies across excerpts, and synthesizing overlapping findings into a coherent evidence table. In addition, SLIDERS allows users to ask follow-up questions in natural language to further explore the assembled evidence. We evaluate SLIDERS on three systematic-review-style tasks over large document collections. SLIDERS outperforms the best-performing baseline across benchmarks, remains near 90% accuracy across 6M-11M-token corpora. On two new follow-up analysis benchmarks SLIDERS can answer 77.9% and 58.3% followup questions accurately.  \nFigure 1: SLIDERS outperforms BM25, LongRAG, and RLM (GPT-5) on all six benchmarks that reflect systematic reviews (left) . It maintains high accuracy as number of documents increase and evidence dispersion grow, where as RLM degrades (right) .  \n∗ Code: [https://github.com/stanford-oval/sliders](https://github.com/stanford-oval/sliders) Website: [https://sliders.genie.stanford.edu/](https://sliders.genie.stanford.edu/)  \nPreprint.  \n1 Introduction  \nSystematic reviews are a cornerstone of evidence-based research across medicine, social sciences, policy analysis, finance, law, and other technical domains [1–5] . These reviews answer pre-specified research questions by collecting and synthesizing evidence from eligible documents [6–10] . The process includes defining a question, selecting relevant documents, extracting evidence variables, reconciling evidence across multiple sources, and producing a transparent synthesis with supporting evidence and caveats [10–14] . Because these steps require sustained expert judgment, manual systematic review production is highly labor-intensive. One PROSPERO-based analysis estimates a mean of 67.3 weeks to complete and publish a review [15–17] .  \nWe study the problem of automating evidence synthesis for systematic-review-style workflows. Given a research question and a corpus of eligible documents, the goal is to identify relevant evidence, preserve enough context to support tractable reasoning, compare findings across sources, and answer both the original question and follow-up questions. This setting creates two technical challenges: how to maintain broad evidence coverage across a large corpus, and how to synthesize accurate, detailed answers from evidence that may be distributed, redundant, incomplete, or conflicting.  \nLarge language models (LLMs) are increasingly used in research, with recent deep research systems [18, 19] surfacing references that manual searches overlook. However, these systems primarily rely on RAG [20–22], where embedding-similarity search is used to select passages for downstream synthesis. This retrieval-first approach is poorly matched to systematic reviews. Technical evidence is often distributed acros","cbCaipcyPKRji9rJ","https://ap.wps.com/l/cbCaipcyPKRji9rJ","pdf",1156257,1,53,"English","en",105,"# Introduction\n## Problem Setting: Evidence Synthesis for Systematic-Review Workflows\n## Limitations of Retrieval-First (RAG) Approaches\n## Limitations of Chunk-Based Extraction Pipelines\n# SLIDERS Methodology","[{\"question\":\"What does SLIDERS aim to automate in systematic-review style workflows?\",\"answer\":\"SLIDERS automates the identification of relevant evidence, extraction into evidence tables, reconciliation of evidence across sources, and evidence-grounded answer synthesis for both original and follow-up questions.\"},{\"question\":\"Why do retrieval-first RAG approaches not work well for systematic reviews?\",\"answer\":\"RAG often retrieves semantically similar passages rather than comprehensive, provenance-tracked evidence; it can miss relevant information or return too many passages, reducing transparency, efficiency, and answer reliability.\"},{\"question\":\"How does SLIDERS reconcile conflicting or fragmented evidence across documents?\",\"answer\":\"An automated evidence reconciliation agent writes code to analyze extracted evidence, reconcile related records, resolve inconsistencies across excerpts, and synthesize overlapping findings into a coherent evidence table.\"}]",1784175052,134,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"sliders-systematic-reviews-via-automated-evidence-synthesis-and-reconciliation","",{"@graph":35,"@context":84},[36,53,67],{"@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/sliders-systematic-reviews-via-automated-evidence-synthesis-and-reconciliation/81640/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What does SLIDERS aim to automate in systematic-review style workflows?","Question",{"text":74,"@type":75},"SLIDERS automates the identification of relevant evidence, extraction into evidence tables, reconciliation of evidence across sources, and evidence-grounded answer synthesis for both original and follow-up questions.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Why do retrieval-first RAG approaches not work well for systematic reviews?",{"text":79,"@type":75},"RAG often retrieves semantically similar passages rather than comprehensive, provenance-tracked evidence; it can miss relevant information or return too many passages, reducing transparency, efficiency, and answer reliability.",{"name":81,"@type":72,"acceptedAnswer":82},"How does SLIDERS reconcile conflicting or fragmented evidence across documents?",{"text":83,"@type":75},"An automated evidence reconciliation agent writes code to analyze extracted evidence, reconcile related records, resolve inconsistencies across excerpts, and synthesize overlapping findings into a coherent evidence table.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]