How Well Do LLMs Perform in Peer Review? Evidence from Finance and Accounting

By Hai Lu, Yichen Luo, Luping Yu

Rating

1654
Battle Count: 51

Relevance

1/10
The paper focuses on academic peer review in finance and accounting. It has no direct application to quantitative trading strategies, market prediction, or portfolio optimization.

Implementation Complexity

4/10
The methodology involves scraping conference websites, PDF text extraction, API calls to LLMs with structured output constraints, and standard logistic regression. It is moderately complex due to data cleaning and matching requirements but uses standard tools.

Reproducibility

3/5
The methodology, prompts, and data construction are fully described in the paper and Internet Appendix. The data consists of public conference papers and public publication records. However, no public code repository is explicitly linked in the provided text, though the analysis uses standard statistical methods (logit) and API calls.

Abstract

Referees increasingly use large language models (LLMs), while finance and accounting journals disagree about whether to allow it. We ask which part of a referee's job the models can do. GPT-4o, whose training data end before the 2024 conference season, referees the papers presented at the 2024 AFA and NBER finance meetings, and we compare its verdicts with publication in the top-three finance journals over the next two years. Papers the model scores one standard deviation higher are 44% more likely to be published, net of author reputation. The result is not driven by look-ahead bias, as the model does not recall the outcomes. The information comes from its judgements of correctness and exposition. Its judgements of originality and significance carry none, and a referee guide that stresses importance does not help. The split between correctness and contribution holds for accounting papers and for a newer model, GPT-5. LLMs can check whether research is right, but not whether it matters. The technical check can go to the model, while the judgement of contribution stays with people.

Links

arXiv:2610.18435 ยท Paper rankings

The interactive Everscope explorer (charts, battles, favorites) loads below.