This work proposes a self-contained two-stage training method, requiring no distillation from a stronger model, no manual annotation, and no pre-existing ICW IF ability, and introduces $\mathsf{ICWBench}$, a benchmark of three verifiable ICW instruction families, each scored on both detectability and answer quality.
Yepeng Liu, Tian-Yi Chen, Xuandong Zhao et al.· 0 citations
This work introduces a novel approach, \textit{CanaryTrace}, to safeguard the ownership of text datasets and effectively detect unauthorized use by RA-LLMs, and demonstrates high query efficiency, detectability, and consistency, along with minimal perturbation to the original dataset, all without compromising the performance of the RAG system.
Yepeng Liu, Xuandong Zhao, D. Song et al.· arXiv.org· 15 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.