Attack-in-the-Chain uses chain-of-thought prompting to iteratively select anchor documents and allocate word-level perturbations, boosting target documents in black-box neural ranking models on MS MARCO and TREC DL19.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking Models
Attack-in-the-Chain uses chain-of-thought prompting to iteratively select anchor documents and allocate word-level perturbations, boosting target documents in black-box neural ranking models on MS MARCO and TREC DL19.