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.
Brown, Benjamin Mann, Nick Ryder, et al
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 2representative citing papers
An off-the-shelf LLM prompted on tokenized Modbus traffic from public ICS datasets matches supervised baselines in normal-versus-critical classification accuracy while generating token-grounded audit records without any model updates.
A neurosymbolic pipeline extracts predicates from offer texts with an LLM and validates them via Logic Tensor Networks, delivering performance comparable to standard models plus built-in interpretability on a real corpus.
This is the first comprehensive survey of OOD generalization methodologies for time series, organized across data distribution, representation learning, and OOD evaluation.
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.
-
Large Language Models as Explainable Cyberattack Detectors for Energy Industrial Control Systems
An off-the-shelf LLM prompted on tokenized Modbus traffic from public ICS datasets matches supervised baselines in normal-versus-critical classification accuracy while generating token-grounded audit records without any model updates.
-
From Large Language Model Predicates to Logic Tensor Networks: Neurosymbolic Offer Validation in Regulated Procurement
A neurosymbolic pipeline extracts predicates from offer texts with an LLM and validates them via Logic Tensor Networks, delivering performance comparable to standard models plus built-in interpretability on a real corpus.
-
Out-of-Distribution Generalization in Time Series: A Survey
This is the first comprehensive survey of OOD generalization methodologies for time series, organized across data distribution, representation learning, and OOD evaluation.