🧑‍🔬 Nihar B. Shah

🏛️ Affiliations

🎓Carnegie Mellon UniversityPittsburgh · United States2016–2026 · 92 papersEmployment · Machine Learning and Computer Sciencecurrent🏢MicrosoftRedmond · United States2015–2026 · 2 paperscurrent🎓University of California, BerkeleyBerkeley · United States2011–2020 · 36 papersEducation🎓Indian Institute of Science BangaloreBengaluru · India2009–2011 · 11 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing (2023 · 84 citations)
   Peer review is overloaded, and human reviewers often miss flaws. Liu and Shah explore whether LLMs could take over parts of the reviewing workload. A pilot challenged nine models to find a deliberately planted error in a short paper: GPT-4 along with eight others, namely StableLM, LLaMa, Alpaca, Dolly, Koala, Vicuna…
2. Usefulness of LLMs as an Author Checklist Assistant for Scientific Papers: NeurIPS'24 Experiment (2024 · 10 citations)
   Large conferences ask authors to fill in compliance checklists, but making sure those answers are accurate is hard to do at scale.

All works

7 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper ReviewingarXiv:2306.00622Ryan Liu, Nihar B. Shah2023 · 84 citations
2. What Can Natural Language Processing Do for Peer Review? ↗arXiv:2405.06563 · no summary yetIlia Kuznetsov et al.2024 · 33 citations
3. Peer Reviews of Peer Reviews: A Randomized Controlled Trial and Other Experiments ↗arXiv:2311.09497 · no summary yetAlexander Goldberg et al.2023 · 32 citations
4. The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems ↗arXiv:2509.08713 · no summary yetZiming Luo, Atoosa Kasirzadeh, Nihar B. Shah2025 · 11 citations
5. How do authors’ perceptions of their papers compare with co-authors’ perceptions and peer-review decisions? ↗PLoS ONE · no summary yetCharvi Rastogi et al.2022 · 11 citations
6. Usefulness of LLMs as an Author Checklist Assistant for Scientific Papers: NeurIPS'24 ExperimentarXiv:2411.03417Alexander Goldberg, Ihsan Ullah, Thanh Gia Hieu Khuong, et al.2024 · 10 citations
7. A Gold Standard Dataset for the Reviewer Assignment Problem ↗arXiv (Cornell University) · no summary yetIvan Stelmakh et al.2023 · 7 citations

🤝 Co-authors here

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

• Benedictus Kent Rachmat
• Zhen Xu

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• PLoS ONE

🔗 Cited by

Papers of our library cite their works 129 times (of the 149,439 papers whose bibliographies we read); 28 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/nihar-b-shah/