Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Steer LLM Latents for Hallucination Detection
Seongheon Park, Xuefeng Du, Min-Hsuan Yeh +2
Hallucinations in LLMs pose a significant concern to their safe deployment in real-world applications. Recent approaches have leveraged the latent space of LLMs for hallucination d…
cs.LG2025
Foundations of Unknown-aware Machine Learning
Xuefeng Du
Ensuring the reliability and safety of machine learning models in open-world deployment is a central challenge in AI safety. This thesis develops both algorithmic and theoretical f…