---
title: "AutoForest — paper by Pronesti et al. (2026)"
description: "An LLM then proposes ICO triplets for each study, and only the triplets that appear in every study are offered as candidates. 28 references."
authors: ["Massimiliano Pronesti", "Angelo Miculescu", "Mohsin Kapdi", "Paul Flanagan", "Oisín Redmond", "Joao H Bettencourt-Silva", "Gurdeep Singh Mannu", "Spiros Denaxas", "Rui Providencia", "Anya Belz", "Yufang Hou"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)"
source: "https://aclanthology.org/2026.acl-demo.13/"
doi: "10.18653/v1/2026.acl-demo.13"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/pronesti-2026-autoforest-automatically-generating-forest-plots/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/pronesti-2026-autoforest-automatically-generating-forest-plots/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/23/) / AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis

# AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis

**Authors:** [Massimiliano Pronesti](https://md.research.elamur.ai/free/en/authors/massimiliano-pronesti/), Angelo Miculescu, Mohsin Kapdi, Paul Flanagan, Oisín Redmond, Joao H Bettencourt-Silva, Gurdeep Singh Mannu, Spiros Denaxas, Rui Providencia, [Anya Belz](https://md.research.elamur.ai/free/en/authors/anya-belz/) and [Yufang Hou](https://md.research.elamur.ai/free/en/authors/yufang-hou/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-demo.13/) · [PDF](https://aclanthology.org/2026.acl-demo.13.pdf) · [DOI 10.18653/v1/2026.acl-demo.13](https://doi.org/10.18653/v1/2026.acl-demo.13) · [OpenAlex](https://openalex.org/W7166865237)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Building forest plots for systematic reviews is still slow, piecemeal work. Reviewers read trial reports, settle on the intervention, comparator and outcome, copy numbers by hand, and then enter structured data into tools such as RevMan. AutoForest is presented as the first system to cover this whole chain, starting from uploaded PDFs and ending with a forest plot ready for publication.

The system has a ReactJS interface on top of a FastAPI backend, and its model components can be swapped out. Documents are converted to Markdown with docling. An LLM then proposes ICO triplets for each study, and only the triplets that appear in every study are offered as candidates. Next, the system extracts binary or continuous outcome data, assesses RoB1/RoB2 risk of bias, and pools results with a fixed- or random-effects model.

In a user study with clinicians and graduate students, AutoForest cut completion time roughly in half and made extraction much more accurate than manual work in RevMan. With the tool, students performed at about the level of experts. This could make meta-analysis faster and easier for non-specialists.

## Key points
- **Comparison with existing tools:** RevMan, CMA, DistillerSR and EPPI-Reviewer were reviewed, and none of them automates ICO suggestion, data extraction, RoB assessment and plotting together.
- **User study design:** 4 clinical experts and 4 graduate students took part in a within-subjects study.
  - Time per task fell from 53.8 to 26.5 min for students and from 70.4 to 29.8 min for experts (p \< 0.001).
- **Data-extraction accuracy:**
  - Fully automatic mode reached 82–83%, compared with 36.9% (students) and 45.8% (experts) when working manually.
  - With human edits, experts reached 90.2% and students 86.4%.
  - Expert RoB accuracy rose from 69.4% to 79.2%.
- **ICO suggestions and RoB reasoning:**
  - Suggested ICO elements had precision of 94.1% for I, 83.3% for C and 94.3% for O.
  - Adding macro-based reasoning raised RoB2 accuracy from 61.6% to 70.8%.
- **Conversion quality and user ratings:**
  - Across 206 tables from 56 studies, docling conversion scored 98.1% on table detection and 93.4% on TEDS.
  - Participants rated professional adoption potential at 4.63/5.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Oxford](https://md.research.elamur.ai/free/en/universities/university-of-oxford/) — University, Oxford, United Kingdom · 104 works · 157,183 citations
- [IBM](https://md.research.elamur.ai/free/en/companies/ibm/) — Company, Armonk, United States · 139 works · 70,691 citations
- [University College London](https://md.research.elamur.ai/free/en/universities/university-college-london/) — University, London, United Kingdom · 88 works · 19,432 citations
- [Dublin City University](https://md.research.elamur.ai/free/en/universities/dublin-city-university/) — University, Dublin, Ireland · 70 works · 9,447 citations
- [Interdisciplinary Transformation University Austria](https://md.research.elamur.ai/free/en/universities/interdisciplinary-transformation-university-austria/) — University, Linz, Austria · 5 works · 35 citations

📚 Shelves (8): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🧬 Biochemistry, Genetics and Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · 234 works · [🧬 Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · 231 works · [🎯 Decision Sciences](https://md.research.elamur.ai/free/en/shelves/decision-sciences/) · 209 works · [🎯 Statistics, Probability and Uncertainty](https://md.research.elamur.ai/free/en/shelves/decision-sciences/statistics-probability-and-uncertainty/) · 61 works

## Cite

Cite as: Massimiliano Pronesti, Angelo Miculescu, Mohsin Kapdi, Paul Flanagan, Oisín Redmond, Joao H Bettencourt-Silva, Gurdeep Singh Mannu, Spiros Denaxas, Rui Providencia, Anya Belz and Yufang Hou. 2026. AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{pronesti2026autoforest,
  title = {{AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis}},
  author = {Massimiliano Pronesti, Angelo Miculescu, Mohsin Kapdi, Paul Flanagan, Oisín Redmond, Joao H Bettencourt-Silva, Gurdeep Singh Mannu, Spiros Denaxas, Rui Providencia, Anya Belz and Yufang Hou},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-demo.13},
  url = {https://doi.org/10.18653/v1/2026.acl-demo.13}
}
```

- [← previous AutoBool: Reinforcement-Learned LLM for Effective Automatic Systematic Reviews Boolean Query Generation](https://md.research.elamur.ai/free/en/papers/wang-2026-autobool-reinforcement-learned-llm-effective/)
- [next → Automated Essay Scoring and Language Certification: Assessing Generalizability, Agreement and Validity for French](https://md.research.elamur.ai/free/en/papers/wilkens-2026-automated-essay-scoring-language-certification/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/23/)

## References

28 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anthropic. 2025. Introducing Claude Sonnet 4.5. [https://www.anthropic.com/news/](https://www.anthropic.com/news/) claude-sonnet-4-5. [↗](https://www.anthropic.com/news/)
2. Christoph Auer, Maksym Lysak, Ahmed Nassar, Michele Dolfi, Nikolaos Livathinos, Panos Vagenas, Cesar Berrospi Ramis, Matteo Omenetti, Fabian Lindlbauer, Kasper Dinkla, Lokesh Mishra, Yusik Kim, Shubham Gupta, Rafael Teixeira de Lima, Valery Weber, Lucas Morin, Ingmar Meijer, Viktor Kuropiatnyk, and… — [arXiv:2408.09869](https://arxiv.org/abs/2408.09869) [find](https://scholar.google.com/scholar?q=Christoph+Auer%2C+Maksym+Lysak%2C+Ahmed+Nassar%2C+Michele+Dolfi%2C+Nikolaos+Livathinos%2C+Panos+Vagenas%2C+Cesar+Berrospi+Ramis%2C+Matteo+Omenetti%2C+Fabian+Lindlbauer%2C+Kasper+Dinkla%2C+Lokesh+Mishra%2C+Yusik+Kim%2C+Shubha)
3. Sara Balduzzi, Gerta Rücker, and Guido Schwarzer. 2019. How to perform a meta-analysis with R: a practical tutorial. Evidence-Based Mental Health, (22):153–160. [find](https://scholar.google.com/scholar?q=Sara+Balduzzi%2C+Gerta+R%C3%BCcker%2C+and+Guido+Schwarzer%2E+2019%2E+How+to+perform+a+meta%2Danalysis+with+R%3A+a+practical+tutorial%2E+Evidence%2DBased+Mental+Health%2C+%2822%29%3A153%E2%80%93160%2E)
4. Leon Bax, Lu Yu, Nobuko Ikeda, and Karel G M Moons. 2007. A systematic comparison of software dedicated to meta-analysis of causal studies. BMC Medical Research Methodology, 7(1):40. [find](https://scholar.google.com/scholar?q=Leon+Bax%2C+Lu+Yu%2C+Nobuko+Ikeda%2C+and+Karel+G+M+Moons%2E+2007%2E+A+systematic+comparison+of+software+dedicated+to+meta%2Danalysis+of+causal+studies%2E+BMC+Medical+Research+Methodology%2C+7%281%29%3A40%2E)
5. Michael Borenstein. 2022. Comprehensive meta-analysis software. In Matthias Egger, Julian P T Higgins, and George Davey Smith, editors, Systematic Reviews in Health Research: Meta-analysis in Context, pages 535–548. Wiley. [find](https://scholar.google.com/scholar?q=Michael+Borenstein%2E+2022%2E+Comprehensive+meta%2Danalysis+software%2E+In+Matthias+Egger%2C+Julian+P+T+Higgins%2C+and+George+Davey+Smith%2C+editors%2C+Systematic+Reviews+in+Health+Research%3A+Meta%2Danalysis+in+Context%2C)
6. DistillerSR Inc. 2023. DistillerSR. Version 2.35. [https://www.distillersr.com/](https://www.distillersr.com/). Accessed June– July 2025. [↗](https://www.distillersr.com/)
7. Julian P. T. Higgins, James Thomas, Jacqueline Chandler, Miranda Cumpston, Tianjing Li, Matthew J. Page, and Vivian A. Welch, editors. 2024. Cochrane Handbook for Systematic Reviews of Interventions, version 6.5 (updated August 2024). Cochrane. Available from [https://training.cochrane.org/handbook](https://training.cochrane.org/handbook). [↗](https://training.cochrane.org/handbook)
8. Julian PT Higgins, Douglas G Altman, Peter C Gøtzsche, Peter Jüni, David Moher, Andrew D Oxman, Jelena Savović, Kenneth F Schulz, Laura Weeks, and Jonathan AC Sterne. 2011. The cochrane collaboration’s tool for assessing risk of bias in randomised trials. bmj, 343. [find](https://scholar.google.com/scholar?q=Julian+PT+Higgins%2C+Douglas+G+Altman%2C+Peter+C+G%C3%B8tzsche%2C+Peter+J%C3%BCni%2C+David+Moher%2C+Andrew+D+Oxman%2C+Jelena+Savovic%CC%81%2C+Kenneth+F+Schulz%2C+Laura+Weeks%2C+and+Jonathan+AC+Sterne%2E+2011%2E+The+cochrane+collaboration)
9. Changkai Ji, Bowen Zhao, Zhuoyao Wang, Yingwen Wang, Yuejie Zhang, Ying Cheng, Rui Feng, and Xiaobo Zhang. 2025. RoBGuard: Enhancing LLMs to assess risk of bias in clinical trial documents. In Proceedings of the 31st International Conference on Computational Linguistics, pages 1258–1277, Abu Dhabi,… [find](https://scholar.google.com/scholar?q=Changkai+Ji%2C+Bowen+Zhao%2C+Zhuoyao+Wang%2C+Yingwen+Wang%2C+Yuejie+Zhang%2C+Ying+Cheng%2C+Rui+Feng%2C+and+Xiaobo+Zhang%2E+2025%2E+RoBGuard%3A+Enhancing+LLMs+to+assess+risk+of+bias+in+clinical+trial+documents%2E+In+Proceed)
10. Qusai Khraisha, Sophie Put, Johanna Kappenberg, Azza Warraitch, and Kristin Hadfield. 2024. Can large language models replace humans in systematic reviews? evaluating GPT-4’s efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages. Research Synthesis Me… [find](https://scholar.google.com/scholar?q=Qusai+Khraisha%2C+Sophie+Put%2C+Johanna+Kappenberg%2C+Azza+Warraitch%2C+and+Kristin+Hadfield%2E+2024%2E+Can+large+language+models+replace+humans+in+systematic+reviews%3F+evaluating+GPT%2D4%E2%80%99s+efficacy+in+screening+and)
11. Honghao Lai, Jiayi Liu, Chunyang Bai, Hui Liu, Bei Pan, Xufei Luo, Liangying Hou, Weilong Zhao, Danni Xia, Jinhui Tian, Yaolong Chen, Lu Zhang, Janne Estill, Jie Liu, Xing Liao, Nannan Shi, Xin Sun, Hongcai Shang, Zhaoxiang Bian, and 17 others. 2025. Language models for data extraction and risk of b… [find](https://scholar.google.com/scholar?q=Honghao+Lai%2C+Jiayi+Liu%2C+Chunyang+Bai%2C+Hui+Liu%2C+Bei+Pan%2C+Xufei+Luo%2C+Liangying+Hou%2C+Weilong+Zhao%2C+Danni+Xia%2C+Jinhui+Tian%2C+Yaolong+Chen%2C+Lu+Zhang%2C+Janne+Estill%2C+Jie+Liu%2C+Xing+Liao%2C+Nannan+Shi%2C+Xin+Sun%2C+H)
12. Nikolaos Livathinos, Christoph Auer, Maksym Lysak, Ahmed Nassar, Michele Dolfi, Panos Vagenas, Cesar Berrospi Ramis, Matteo Omenetti, Kasper Dinkla, Yusik Kim, Shubham Gupta, Rafael Teixeira de Lima, Valery Weber, Lucas Morin, Ingmar Meijer, Viktor Kuropiatnyk, and Peter W. J. Staar. 2025a. Docling:… — [arXiv:2501.17887](https://arxiv.org/abs/2501.17887) [find](https://scholar.google.com/scholar?q=Nikolaos+Livathinos%2C+Christoph+Auer%2C+Maksym+Lysak%2C+Ahmed+Nassar%2C+Michele+Dolfi%2C+Panos+Vagenas%2C+Cesar+Berrospi+Ramis%2C+Matteo+Omenetti%2C+Kasper+Dinkla%2C+Yusik+Kim%2C+Shubham+Gupta%2C+Rafael+Teixeira+de+Lima%2C+)
13. Nikolaos Livathinos, Christoph Auer, Ahmed Nassar, Rafael Teixeira de Lima, Maksym Lysak, Brown Ebouky, Cesar Berrospi, Michele Dolfi, Panagiotis Vagenas, Matteo Omenetti, Kasper Dinkla, Yusik Kim, Valery Weber, Lucas Morin, Ingmar Meijer, Viktor Kuropiatnyk, Tim Strohmeyer, A. Said Gurbuz, and Pete… [find](https://scholar.google.com/scholar?q=Nikolaos+Livathinos%2C+Christoph+Auer%2C+Ahmed+Nassar%2C+Rafael+Teixeira+de+Lima%2C+Maksym+Lysak%2C+Brown+Ebouky%2C+Cesar+Berrospi%2C+Michele+Dolfi%2C+Panagiotis+Vagenas%2C+Matteo+Omenetti%2C+Kasper+Dinkla%2C+Yusik+Kim%2C+Va)
14. Iain J. Marshall and Byron C. Wallace. 2019. Toward systematic review automation: a practical guide to using machine learning tools in research synthesis. Systematic Reviews, 8(1):163. [find](https://scholar.google.com/scholar?q=Iain+J%2E+Marshall+and+Byron+C%2E+Wallace%2E+2019%2E+Toward+systematic+review+automation%3A+a+practical+guide+to+using+machine+learning+tools+in+research+synthesis%2E+Systematic+Reviews%2C+8%281%29%3A163%2E)
15. Sandra McMillan, Caroline Hamel, Sharon E Kelly, Kanokporn Thavorn, David B Rice, George A Wells, and Bonnie Hutton. 2020. An evaluation of distillerSR’s machine learning-based prioritization tool for title/abstract screening–impact on reviewer-relevant outcomes. BMC Medical Research Methodology, 20… [find](https://scholar.google.com/scholar?q=Sandra+McMillan%2C+Caroline+Hamel%2C+Sharon+E+Kelly%2C+Kanokporn+Thavorn%2C+David+B+Rice%2C+George+A+Wells%2C+and+Bonnie+Hutton%2E+2020%2E+An+evaluation+of+distillerSR%E2%80%99s+machine+learning%2Dbased+prioritization+tool+for)
16. Matthew Michelson and Katja Reuter. 2019. The significant cost of systematic reviews and meta-analyses: a call for greater involvement of machine learning to assess the promise of clinical trials. Contemporary Clinical Trials Communications, 16:100443. [find](https://scholar.google.com/scholar?q=Matthew+Michelson+and+Katja+Reuter%2E+2019%2E+The+significant+cost+of+systematic+reviews+and+meta%2Danalyses%3A+a+call+for+greater+involvement+of+machine+learning+to+assess+the+promise+of+clinical+trials%2E+Con)
17. M. Hassan Murad, Noor Asi, Mouaz Alsawas, and Fares Alahdab. 2016. New evidence pyramid. Evidence-Based Medicine, 21(4):125–127. [find](https://scholar.google.com/scholar?q=M%2E+Hassan+Murad%2C+Noor+Asi%2C+Mouaz+Alsawas%2C+and+Fares+Alahdab%2E+2016%2E+New+evidence+pyramid%2E+Evidence%2DBased+Medicine%2C+21%284%29%3A125%E2%80%93127%2E)
18. Massimiliano Pronesti, Anya Belz, and Yufang Hou. 2026. [Beyond outcome verification: Verifiable Process Reward Models for structured reasoning](https://md.research.elamur.ai/free/en/papers/pronesti-2026-beyond-outcome-verification-verifiable-process/). In Findings of the Association for Computational Linguistics: ACL 2026, San Diego, California, USA. Association for Computational Linguistics.
19. Massimiliano Pronesti, Joao H Bettencourt-Silva, Paul Flanagan, Alessandra Pascale, Oisín Redmond, Anya Belz, and Yufang Hou. 2025a. Query-driven document-level scientific evidence extraction from biomedical studies. In Proceedings of the 63rd Annual Meeting of the Association for Computational Ling… [find](https://scholar.google.com/scholar?q=Massimiliano+Pronesti%2C+Joao+H+Bettencourt%2DSilva%2C+Paul+Flanagan%2C+Alessandra+Pascale%2C+Ois%C3%ADn+Redmond%2C+Anya+Belz%2C+and+Yufang+Hou%2E+2025a%2E+Query%2Ddriven+document%2Dlevel+scientific+evidence+extraction+from+bio)
20. Massimiliano Pronesti, Michela Lorandi, Paul Flanagan, Oisín Redmond, Anya Belz, and Yufang Hou. 2025b. Enhancing study-level inference from clinical trial papers via reinforcement learning-based numeric reasoning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Proces… [find](https://scholar.google.com/scholar?q=Massimiliano+Pronesti%2C+Michela+Lorandi%2C+Paul+Flanagan%2C+Ois%C3%ADn+Redmond%2C+Anya+Belz%2C+and+Yufang+Hou%2E+2025b%2E+Enhancing+study%2Dlevel+inference+from+clinical+trial+papers+via+reinforcement+learning%2Dbased+nume)
21. Rui Qiu, Shijie Chen, Yu Su, Po-Yin Yen, and Han Wei Shen. 2025. Completing a systematic review in hours instead of months with interactive AI agents. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 31559–31593, Vienna, Austri… [find](https://scholar.google.com/scholar?q=Rui+Qiu%2C+Shijie+Chen%2C+Yu+Su%2C+Po%2DYin+Yen%2C+and+Han+Wei+Shen%2E+2025%2E+Completing+a+systematic+review+in+hours+instead+of+months+with+interactive+AI+agents%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+)
22. Jonathan AC Sterne, Jelena Savović, Matthew J. Page, Roy G. Elbers, Natalie S. Blencowe, Isabelle Boutron, Christopher J. Cates, He Cheng, Mark S. Corbett, Sandra M. Eldridge, Miguel A. Hernán, Sally Hopewell, Asbjørn Hróbjartsson, Diana R. Junqueira, Peter Jüni, Jamie J. Kirkham, Toby Lasserson, T… [find](https://scholar.google.com/scholar?q=Jonathan+AC+Sterne%2C+Jelena+Savovic%CC%81%2C+Matthew+J%2E+Page%2C+Roy+G%2E+Elbers%2C+Natalie+S%2E+Blencowe%2C+Isabelle+Boutron%2C+Christopher+J%2E+Cates%2C+He+Cheng%2C+Mark+S%2E+Corbett%2C+Sandra+M%2E+Eldridge%2C+Miguel+A%2E+Hern%C3%A1n%2C+Sally)
23. Zhuanlan Sun, Ruilin Zhang, Suhail A Doi, Luis Furuya-Kanamori, Tianqi Yu, Lifeng Lin, and Chang Xu. 2024. How good are large language models for automated data extraction from randomized trials? medRxiv, pages 2024–02. [find](https://scholar.google.com/scholar?q=Zhuanlan+Sun%2C+Ruilin+Zhang%2C+Suhail+A+Doi%2C+Luis+Furuya%2DKanamori%2C+Tianqi+Yu%2C+Lifeng+Lin%2C+and+Chang+Xu%2E+2024%2E+How+good+are+large+language+models+for+automated+data+extraction+from+randomized+trials%3F+medR)
24. The Cochrane Collaboration. 2020. Review manager (revman) [computer program]. [https://training.cochrane.org/online-learning/](https://training.cochrane.org/online-learning/) core-software-cochrane-reviews/revman/ revman-5-download. Version 5.4. [↗](https://training.cochrane.org/online-learning/)
25. James Thomas, Julie Brunton, and Silvia Graziosi. 2010. EPPI-reviewer 4.0: software for research synthesis. Technical report, EPPI-Centre, UCL. [find](https://scholar.google.com/scholar?q=James+Thomas%2C+Julie+Brunton%2C+and+Silvia+Graziosi%2E+2010%2E+EPPI%2Dreviewer+4%2E0%3A+software+for+research+synthesis%2E+Technical+report%2C+EPPI%2DCentre%2C+UCL%2E)
26. Jianyou Wang, Weili Cao, Longtian Bao, Youze Zheng, Gil Pasternak, Kaicheng Wang, Xiaoyue Wang, Ramamohan Paturi, and Leon Bergen. 2025. Measuring risk of bias in biomedical reports: The RoBBR benchmark. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages… [find](https://scholar.google.com/scholar?q=Jianyou+Wang%2C+Weili+Cao%2C+Longtian+Bao%2C+Youze+Zheng%2C+Gil+Pasternak%2C+Kaicheng+Wang%2C+Xiaoyue+Wang%2C+Ramamohan+Paturi%2C+and+Leon+Bergen%2E+2025%2E+Measuring+risk+of+bias+in+biomedical+reports%3A+The+RoBBR+benchma)
27. Zifeng Wang, Lang Cao, Benjamin Danek, Qiao Jin, Zhiyong Lu, and Jimeng Sun. 2024. Accelerating clinical evidence synthesis with large language models. NPJ Digital Medicine. [find](https://scholar.google.com/scholar?q=Zifeng+Wang%2C+Lang+Cao%2C+Benjamin+Danek%2C+Qiao+Jin%2C+Zhiyong+Lu%2C+and+Jimeng+Sun%2E+2024%2E+Accelerating+clinical+evidence+synthesis+with+large+language+models%2E+NPJ+Digital+Medicine%2E)
28. Hye Sun Yun, David Pogrebitskiy, Iain James Marshall, and Byron C Wallace. 2024. Automatically extracting numerical results from randomized controlled trials with large language models. In Machine Learning for Healthcare Conference. PMLR. [find](https://scholar.google.com/scholar?q=Hye+Sun+Yun%2C+David+Pogrebitskiy%2C+Iain+James+Marshall%2C+and+Byron+C+Wallace%2E+2024%2E+Automatically+extracting+numerical+results+from+randomized+controlled+trials+with+large+language+models%2E+In+Machine+Lea)

*Updated 1 November 2026*