Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.14165 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908984572641280 |
|---|---|
| author | Ahuja, Naman Mulla, Saniya Khan, Muhammad Ali Riaz, Zaryab Bin Khakwani, Kaneez Zahra Rubab Sonbol, Mohamad Bassam Riaz, Irbaz Bin Gupta, Vivek |
| author_facet | Ahuja, Naman Mulla, Saniya Khan, Muhammad Ali Riaz, Zaryab Bin Khakwani, Kaneez Zahra Rubab Sonbol, Mohamad Bassam Riaz, Irbaz Bin Gupta, Vivek |
| contents | We present EviSearch, a multi-agent extraction system that automates the creation of ontology-aligned clinical evidence tables directly from native trial PDFs while guaranteeing per-cell provenance for audit and human verification. EviSearch pairs a PDF-query agent (which preserves rendered layout and figures) with a retrieval-guided search agent and a reconciliation module that forces page-level verification when agents disagree. The pipeline is designed for high-precision extraction across multimodal evidence sources (text, tables, figures) and for generating reviewer-actionable provenance that clinicians can inspect and correct. On a clinician-curated benchmark of oncology trial papers, EviSearch substantially improves extraction accuracy relative to strong parsed-text baselines while providing comprehensive attribution coverage. By logging reconciler decisions and reviewer edits, the system produces structured preference and supervision signals that bootstrap iterative model improvement. EviSearch is intended to accelerate living systematic review workflows, reduce manual curation burden, and provide a safe, auditable path for integrating LLM-based extraction into evidence synthesis pipelines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14165 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EviSearch: A Human in the Loop System for Extracting and Auditing Clinical Evidence for Systematic Reviews Ahuja, Naman Mulla, Saniya Khan, Muhammad Ali Riaz, Zaryab Bin Khakwani, Kaneez Zahra Rubab Sonbol, Mohamad Bassam Riaz, Irbaz Bin Gupta, Vivek Computation and Language We present EviSearch, a multi-agent extraction system that automates the creation of ontology-aligned clinical evidence tables directly from native trial PDFs while guaranteeing per-cell provenance for audit and human verification. EviSearch pairs a PDF-query agent (which preserves rendered layout and figures) with a retrieval-guided search agent and a reconciliation module that forces page-level verification when agents disagree. The pipeline is designed for high-precision extraction across multimodal evidence sources (text, tables, figures) and for generating reviewer-actionable provenance that clinicians can inspect and correct. On a clinician-curated benchmark of oncology trial papers, EviSearch substantially improves extraction accuracy relative to strong parsed-text baselines while providing comprehensive attribution coverage. By logging reconciler decisions and reviewer edits, the system produces structured preference and supervision signals that bootstrap iterative model improvement. EviSearch is intended to accelerate living systematic review workflows, reduce manual curation burden, and provide a safe, auditable path for integrating LLM-based extraction into evidence synthesis pipelines. |
| title | EviSearch: A Human in the Loop System for Extracting and Auditing Clinical Evidence for Systematic Reviews |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.14165 |