activity
20242026
most citedLarge Language Models for In-File Vulnerability Localization Can Be "Lost in the End"

9 citations · 22 across the 13 of their papers we have counts for

collaborators
Showing 2025 · cs.AIShow all

1 paper · 2 filters

cs.AI2025

Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP

Francesco Sovrano

Large language models (LLMs) can amplify misinformation, undermining societal goals such as the UN SDGs. We study three documented drivers of misinformation (valence framing, infor…