🧑‍🔬 Mark Gerstein

Affiliations

• Yale University · New Haven, United States — current · 1997–2026 on 945 papers · employment (Wikidata)
• Yale Cancer Center · New Haven, United States — current · 2017–2026 on 2 papers
• Harvard University · Cambridge, United States — 2004–2025 on 10 papers · education (Wikidata)
• European Bioinformatics Institute · Cambridge, United Kingdom — 2020–2024 on 14 papers
• Peking University · Beijing, China — 2003–2024 on 3 papers
• New York University · New York, United States — 2023–2024 on 2 papers
• Zhejiang University · Hangzhou, China — 2023–2024 on 2 papers
• Broad Institute · Cambridge, United States — 2020–2023 on 21 papers
• Princeton University · Princeton, United States — 2020–2023 on 11 papers
• National Institute of Environmental Health Sciences · Durham, United States — 2020–2023 on 8 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 79 more institutions on single bylines are not listed.

Topics

Language models & pretraining1Evaluation & benchmarks1Reasoning1

Works by year

2020s

Papers

The most cited first (OpenAlex and our library).

1. MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning (2024 · 244 citations)
   LLMs handle many general tasks well, but medical questions remain hard. The field relies on specialized terminology, public clinical training data is scarce, and plain prompting often fails to bring out expert knowledge or invites hallucination. MedAgents addresses this with a training-free, zero-shot framework that…
2. Investigating Data Contamination in Modern Benchmarks for Large Language Models (2024 · 137 citations)
   Benchmark scores of large language models may be inflated if test items leaked into their training data. For proprietary models, and for many open ones, the training data cannot be inspected. The authors look at this contamination problem from two sides.

Also in our library

3 more works of theirs are in our library without a page here yet; they will appear as we publish them.

Co-authors here

4 co-authors with a page, the most papers together first.

• Arman Cohan ×2
• Xiangru Tang ×2
• Yilun Zhao ×2
• Zhuosheng Zhang

Cited by

Papers of our library cite their works 735 times (of the 140 884 papers whose bibliographies we read); 40 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/mark-gerstein/