SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation
Not on the map. Why?
Abstract (arXiv)
Systematic 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
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 66 references that are in the map. First posted on arXiv 24 Apr 2026.
Builds on
16 of 66 references.
References · 16
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
- 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
- 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
- 2023Evaluating Verifiability in Generative Search Enginescited by 303
- 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
- 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 246
- 2025BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agentcited by 200
- 2024Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QAcited by 122
- 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 108
- 2025Recursive Language Modelscited by 104
4 more
- 2025Cartridges: Lightweight and general-purpose long context representations via self-studycited by 86
- 2025Oolong: Evaluating Long Context Reasoning and Aggregation Capabilitiescited by 40
- 2024Docling Technical Reportcited by 34
- 2025FinSage: A Multi-aspect RAG System for Financial Filings Question Answeringcited by 19
Built on by
Citing papers per year: 2026: 2.
2 papers.