29th International Conference on Computer and Information Technology (ICCIT 2026), Bangladesh ·
How Prompt Injection Changes LLM-Generated Peer Reviews: A Discourse Analysis
Accepted · Conference · AI safety
Generic prompt injection raised scores and reduced criticism in AI-generated peer reviews.
Abstract
Large language models are increasingly used to support peer review, yet the manuscripts they assess may contain instructions that redirect the review process. Such prompt injections can affect not only numerical recommendations but also the evidence, criticism, and reasoning expressed in generated reviews. We investigate this risk through a controlled study of 288 ICLR 2024 papers reviewed by three open-weight models under clean, explicit-generic (EG), targeted-specific (TS), and targeted-misdirect (TM) conditions, yielding 10,352 successful reviews. We characterize output changes with transparent discourse representations: D32 deterministic features, T18 sentence-graph features, and their F50 combination. EG raises the mean score by 2.11 points and sharply reduces critique density and weakness proportion from 10.23 to 2.83 and from 0.193 to 0.025, respectively. D32 and F50 achieve 0.991 AUROC for clean-versus-EG separation; a length-and-format baseline reaches 0.985, while residualized D32 retains 0.812 after word-count adjustment. TS and TM produce small score shifts and near-chance separation. These findings show how discourse analysis reveals changes in review reasoning and provides a transparent basis for auditing the integrity of LLM-assisted peer review.
Findings
- Generic prompt injection raised mean review scores by 2.11 points and reduced the share of text devoted to weaknesses from 0.193 to 0.025.
- Deterministic discourse features distinguished clean reviews from reviews affected by generic injection with 0.812 AUROC after word-count adjustment.
- The two targeted conditions produced small score shifts, and the discourse features separated their reviews from clean reviews at near-chance levels.
Sources and citation
This paper has been accepted. A public proceedings record is pending.
View BibTeX citation
@inproceedings{peer-review-prompt-injection-2026,
title = {{How Prompt Injection Changes LLM-Generated Peer Reviews: A Discourse Analysis}},
author = {BHVSP Subrahmanyam and Saiankit Shankar and Appana Saketh Krishna Rao and Neeraj Choudhary},
booktitle = {29th International Conference on Computer and Information Technology (ICCIT 2026), Bangladesh},
year = {2026},
note = {Accepted}
}