AI peer review systems are vulnerable to prompt injections, prestige biases, assertion strength effects, and contextual poisoning, as demonstrated by a new attack taxonomy and causal experiments on real conference submissions.
AI-assisted peer review
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
unclear 1representative citing papers
The RAG-XAI framework detects AI-written peer reviews at 99.61% accuracy by extracting markers like repetition and missing personal signals, while warning that machine review systems could homogenize scientific output.
citing papers explorer
-
When AI reviews science: Can we trust the referee?
AI peer review systems are vulnerable to prompt injections, prestige biases, assertion strength effects, and contextual poisoning, as demonstrated by a new attack taxonomy and causal experiments on real conference submissions.
-
Are we still able to recognize pearls? Machine-driven peer review and the risk to creativity: An explainable RAG-XAI detection framework with markers extraction
The RAG-XAI framework detects AI-written peer reviews at 99.61% accuracy by extracting markers like repetition and missing personal signals, while warning that machine review systems could homogenize scientific output.