Evaluating the Efficacy of Large Language Models in Automating Academic Peer Reviews
Bibliographic record
Abstract
This paper explores the application of large language models (LLMs) in automating the peer review process for academic papers, a critical area for enhancing the efficiency and consistency of scholarly publication. We utilized GPT-4-0125 to automatically generate reviews for 20 papers sourced from openreview.net and analyzed the AI-generated peer reviews for quality and effectiveness. The analysis includes a detailed assessment of the text properties of the reviews, such as sentiment, revealing that LLM-generated reviews tend to be more uniformly positive than their human-written counterparts. In addition, we conducted a user survey in which participants attempted to distinguish between AI-generated and human-written reviews. The survey results indicated a low correct identification rate, suggesting that participants often could not discern the origin of the review, thereby highlighting the potential of LLMs to mimic human-like review qualities. However, the study also identifies limitations in LLM's performance, particularly concerning the variability in review quality, which appears to correlate with the model's vocabulary usage of the generated content.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.028 | 0.109 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".