SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Abdaljalil, Samir, Pallucchini, Filippo, Seveso, Andrea, Kurban, Hasan, Mercorio, Fabio, Serpedin, Erchin
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2503.03032