Factual Yet One-Sided: Stance Poisoning and Evidence Balancing in Retrieval-Augmented Generation
The stance expressed in responses from retrieval-augmented generation systems is significantly influenced by the stance distribution of the retrieved materials. Existing research on knowledge poisoning has primarily targeted factual errors. In contrast, this study focuses on injection attacks in which the facts are cor...
Pu-Yuan Yang, Shao-Xuan Dong, Liu-Jie Wu et al.
· 0 citations