Author

Aleksandr Rubashevskii

h-index 5 View on Semantic Scholar

We have 1 of 9 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

MIRAGE: Defending Long-Form RAG Against Misinformation Pollution

MIRAGE, a training-free, model-agnostic defense for long-form RAG, is introduced, a training-free, model-agnostic defense for long-form RAG that consistently restores factuality under mixed and fully polluted evidence and outperforms prior robust-RAG methods.

Saadeldine Eletter, Ruihong Zeng, Yuxia Wang et al. · arXiv.org · 0 citations