Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Knowing When Not to Answer: Lightweight KB-Aligned OOD Detection for Safe RAG
Ilias Triantafyllopoulos, Renyi Qu, Salvatore Giorgi +3
Retrieval-Augmented Generation (RAG) systems are increasingly deployed in high-stakes domains, where safety depends not only on how a system answers, but also on whether a query sh…
cs.CL2025
Interpreting and Mitigating Unwanted Uncertainty in LLMs
Tiasa Singha Roy, Ayush Rajesh Jhaveri, Ilias Triantafyllopoulos
Despite their impressive capabilities, Large Language Models (LLMs) exhibit unwanted uncertainty, a phenomenon where a model changes a previously correct answer into an incorrect o…