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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Data-driven friendliness model for virtual agents improves perceived friendliness by 5.71% and social presence by 4.03% in AR user study with HoloLens integration.
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.
-
FVA: Modeling Perceived Friendliness of Virtual Agents Using Movement Characteristics
Data-driven friendliness model for virtual agents improves perceived friendliness by 5.71% and social presence by 4.03% in AR user study with HoloLens integration.