Human-in-the-loop AI reviewing: Feasibility, opportunities, and risks
Abstract
The promise of AI for academic work is bewitching and easy to envisage, but the risks involved are often hard to detect and usually not readily exposed. In this opinion piece, we explore the feasibility, opportunities, and risks of using large language models (LLMs) for reviewing academic submissions, while keeping the human in the loop. We experiment with GPT-4 in the role of a reviewer to demonstrate the opportunities and the risks we experience and ways to mitigate them. The reviews are structured according to a conference review form with the dual purpose of evaluating submissions for editorial decisions and providing authors with constructive feedback according to predefined criteria, which include contribution, soundness, and presentation. We demonstrate feasibility by evaluating and comparing LLM reviews with human reviews, concluding that current AI-augmented reviewing is sufficiently accurate to alleviate the burden of reviewing but not completely and not for all cases. We then enumerate the opportunities of AI-augmented reviewing and present open questions. Next, we identify the risks of AI-augmented reviewing, highlighting bias, value misalignment, and misuse. We conclude with recommendations for managing these risks.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
LLMs exhibit limitations in detecting deeper theoretical flaws, identifying missing metrics, and recognizing instances of overstated conclusions.
“Beyond these issues, LLMs exhibit limitations in detecting deeper theoretical flaws, identifying missing metrics, and recognizing instances of overstated conclusions (Drori & Te'eni, 2024).”
From Large language models for automated scholarly paper review: A survey (2025) · cites this paper as Drori & Te'eni, 2024
Cites
Still being checked.
Cited by
Sorted by citations
A review of large language models and autonomous agents in chemistry
Ramos, M. C., Collison, C. J., & White, A. D. (2025) · Chemical Science · doi:10.1039/d4sc03921a · Cited by 274 · see citing works
Chow, J. C. L., & Li, K. (2025) · Information · doi:10.3390/info16070549 · Cited by 84 · see citing works
Communications of the Association for Information SystemsPreprint
Marabelli, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5250701 · Cited by 59 · see citing works
Opportunities and challenges of using generative AI to personalize educational assessment
Arslan, B., Lehman, B., Tenison, C., Sparks, J. R., López, A. A., Gu, L., & Zapata-Rivera, D. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1460651 · Cited by 52 · see citing works
Tingelhoff, F., Brugger, M., & Leimeister, J. M. (2024) · Journal of Information Technology · doi:10.1177/02683962241304105 · Cited by 53 · see citing works
Large language models for automated scholarly paper review: A survey
Zhuang, Z., Chen, J., Xu, H., Jiang, Y., & Lin, J. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103332 · Cited by 34 · see citing works
Lazaros, K., Vrahatis, A. G., & Kotsiantis, S. (2026) · Entropy · doi:10.3390/e28040377 · Cited by 50 · see citing works
Mollel, M. H. N., Quiroz, L. F., Varley, C., Firestine, A., McLoughlin, M.-E., Kafunah, J., Kharkar, S., O'Farrell, J., Ndlovu, N., Johnston, A., et al. (2025) · Frontiers in Sustainable Food Systems · doi:10.3389/fsufs.2025.1462328 · Cited by 30 · see citing works
Ray, P. P. (2026) · Expert Systems · doi:10.1111/exsy.70213 · Cited by 31 · see citing works
Bayani, A., Ewane, L. P. E., dos Anjos, D. S. O., Mac-Seing, M., & Nikiema, J. N. (2025) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2025.106048 · Cited by 21 · see citing works
Bendig, D., & Bräunche, A. (2024) · Management Review Quarterly · doi:10.1007/s11301-024-00451-y · Cited by 22 · see citing works
Large language models in peer review: challenges and opportunities
Sun, Z. (2025) · Scientometrics · doi:10.1007/s11192-025-05440-w · Cited by 15 · see citing works
Organizational learning for exploring Generative AI: CORE-sandbox experiments
Te’eni, D., Raymond, M., Rowe, F., Thenoz, É., & Trimborn, P. (2026) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2026.103029 · Cited by 10 · see citing works
Self-citationHuman-in-the-Loop Models for Ethical AI Grading: Combining AI Speed with Human Ethical Oversight
Selvam, M., & Vallejo, R. G. (2025) · EthAIca · doi:10.56294/ai2025413 · Cited by 10 · see citing works
Crystalline Material Discovery in the Era of Artificial Intelligence
Wang, Z., Hua, H., Lin, W., Yang, M., & Tan, K. C. (2026) · ACM Computing Surveys · doi:10.1145/3794853 · Cited by 18 · see citing works
Adversarial Machine Learning in IoT Security: A Comprehensive Survey
Huma, Z. E., Jan, S. U., Ahmad, J. E., Buchanan, W. J., & Pitropakis, N. (2025) · ACM Computing Surveys · doi:10.1145/3785665 · Cited by 11 · see citing works
What Can Natural Language Processing Do for Peer Review?
Kuznetsov, I., Afzal, O. M., Dercksen, K., Dycke, N., Goldberg, A., Hope, T., Hovy, D., Kummerfeld, J. K., Lauscher, A., Leyton-Brown, K., et al. (2024) · arXiv · doi:10.48550/arxiv.2405.06563 · Cited by 6 · see citing works
Beyond AI disclosure: Claim accountability and responsible research in scholarly publishing
van Zoonen, W., Morgan‐Thomas, A., & Tursunbayeva, A. (2026) · European Management Journal · doi:10.1016/j.emj.2026.06.001 · Cited by 6 · see citing works
An Analysis of Tasks and Datasets in Peer Reviewing
Staudinger, M., Kusa, W., Piroi, F., & Hanbury, A. (2024) · Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024) · doi:10.18653/v1/2024.sdp-1.24 · Cited by 6 · see citing works
Lim, H., Choi, D., & Hong, H. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732207 · Cited by 4 · see citing works
Large Model Era: Deep Learning in Osteoporosis Drug Discovery
Xu, J., Wen, X., Sun, L. J., Xing, K., Xue, L., Zhou, S., Hu, J., Ai, Z., Kong, Q., Wen, Z., et al. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c02264 · Cited by 5 · see citing works
What are the limits to biomedical research acceleration through general-purpose AI?
Hebenstreit, K., Convalexius, C., Reichl, S., Huber, S. E., Bock, C., & Samwald, M. (2026) · Scientific Reports · doi:10.1038/s41598-025-32583-w · Cited by 3 · see citing works
Steingard, D. S., & Rodenburg, K. S. (2025) · Learned Publishing · doi:10.1002/leap.2010 · Cited by 3 · see citing works
Huynh, M.-T. (2025) · Information Systems Frontiers · doi:10.1007/s10796-025-10647-6 · Cited by 5 · see citing works
Chan, Y. (2025) · Management Learning · doi:10.1177/13505076251377550 · Cited by 2 · see citing works
Extending Test-driven development to Softwarized Networks and Intent Based Networking
Berardi, D., Fontana, M., & Martini, B. (2025) · International Conference on Network and Service Management (CNSM) · doi:10.23919/cnsm67658.2025.11297527 · Cited by 2 · see citing works
Relationship between peer review quality and scientific impact: Insights from LLMs-assessed reviews
Sun, Z. (2026) · Journal of Informetrics · doi:10.1016/j.joi.2026.101801 · Cited by 3 · see citing works
Sun, Q., Liu, D., Dong, H., & Li, S. (2026) · Scientometrics · doi:10.1007/s11192-026-05539-8 · Cited by 1 · see citing works
Marrocco, G. (2026) · IEEE Antennas and Propagation Magazine · doi:10.1109/map.2025.3635559 · Cited by 1 · see citing works
Njuguna, G. N., & Min, Q. (2026) · AI & Society · doi:10.1007/s00146-026-02973-3 · Cited by 1 · see citing works
From AI to AGI: a human-in-the-loop framework for responsible IS futures
Cingillioglu, I., & Lun, P. (2026) · Enterprise Information Systems · doi:10.1080/17517575.2026.2653244 · Cited by 1 · see citing works
The Present and Future of AI: Ethical Issues and Research Opportunities
Srivastava, A., Marabelli, M., Blanch‐Hartigan, D., Moriarty, J., Carey, E., Persky, S., & Torous, J. B. (2025) · Communications of the Association for Information Systems · doi:10.17705/1cais.05611 · Cited by 1 · see citing works
Reciprocal Human-AI Collaboration: Designing Configuration and Delegation for Continual Learning
Te’eni, D. (2025) · Progress in IS · doi:10.1007/978-3-031-83512-4_11 · Cited by 1 · see citing works
Self-citationHarnessing Generative AI to Drive Responsible Business Research and Accelerate Social ImpactPreprint
Steingard, D. S., Reibstein, D. J., & Normandin, M. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5016963 · Cited by 1 · see citing works
Sun, Q., Liu, D., Dong, H., & Li, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5021843
LAYING THE GROUNDWORK: AI IN MATURITY MODEL DEVELOPMENT, SERIES PART 1
Draper, D. C., & Joe, M. (2024) · Performance Improvement Journal · doi:10.56811/pij-25-0005
Architectural Gaps in Generative AI: Quantifying Cognitive Risks for Safety Applications
Wen, H., & Hu, P. (2025) · AI · doi:10.3390/ai6070138
Liu, H., Dai, L., & Jiang, H. (2025) · Applied Sciences · doi:10.3390/app151910696
Security Risks in Large Language Models and General Mitigation Strategies
Zhang, R., & Kanyane, M. H. (2025) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-13075-4_1
Strategic Integration of Large Language Models for Business Transformation
Cruz, E. D. L. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-3912-2.ch013
Retrieval-Augmented Generation
Yu, J. S., & Yao, Y. (2026) · Springer eBooks · doi:10.1007/978-981-95-4632-9_4
Adopting an AI-Assisted Thematic Approach
McTaggart, V., & McCarthy, J. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0434-0.ch002
McTaggart, V. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/406014
LMs4Net: LM-Aided Wireless Network Optimization
Du, H., Chen, X., Liu, Y., & Huang, K. (2026) · Wireless networks · doi:10.1007/978-3-032-20194-2_5
Design Science Research in an Era of Generative AI—Challenges and Theoretical Guidelines
Heiden, P. Z., Beverungen, D., Bartelheimer, C., & Breidbach, C. F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-28313-9_22
Far, S. B., Qazani, M. R. C., Hamod, F. Y. H., & Rad, A. I. (2026) · Engineering Reports · doi:10.1002/eng2.70941
Zhou, X. (2026) · Applied Psychological Measurement · doi:10.1177/01466216261471171
Human-in-the-Loop in MLOps: A Systematic Review on Balancing Automation and Human Oversight
Klüter, L., Kementzey, D., Najafabadi, F. A., Rajenthiram, K., & Gerostathopoulos, I. (2026) · IEEE International Conference on Software Architecture Companion (ICSA-C) · doi:10.1109/icsa-c68850.2026.00055
Towards Automated Analysis of Scientific Limitations and FutureWork
Azher, I. A. (2026) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/3805696.3847130
Subaşı, G., & Şenman, İ. (2026) · Frontiers in Education · doi:10.3389/feduc.2026.2003621
Valentine Joseph Owan, P. D., Owan, M. V., & Akpandem, E. E. (2026) · Educational Point · doi:10.71176/edup/19655
- Authors
- Drori, I., Boston University / Columbia University, Te'eni, D., & Tel Aviv University
- ORCID
- Drori, Iddo
- Venue
- Journal of the Association for Information Systems
- Publisher
- Association for Information Systems
- Published
- 2024
- Volume
- 25
- Issue
- 1
- Pages
- 98-109
- ISSN
- 1536-9323 (ISSN-L)
- OpenAlex
- W4390491459
- Cited by
- 48
- References
- 0
- Citations by year
- 2026: 22 · 2025: 19 · 2024: 7
- FWCI
- 19.98
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of the Association for Information Systems (publishedVersion)
- Journal of the Association for Information Systems (submittedVersion)
- Topics
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Publishing and Scholarly Communication
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Academic Writing and Publishing
- Keywords
- large language models, GPT-4, human-in-the-loop review, scholarly publishing, reviewer bias, value misalignment, AI misuse, author feedback
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
