8 citations · 10 across the 6 of their papers we have counts for
7 papers · 1 filter
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…
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…
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
Xuefeng Du, Chaowei Xiao, Yixuan Li
The surge in applications of large language models (LLMs) has prompted concerns about the generation of misleading or fabricated information, known as hallucinations. Therefore, de…
Out-of-Distribution Learning with Human Feedback
Haoyue Bai, Xuefeng Du, Katie Rainey +2
Out-of-distribution (OOD) learning often relies heavily on statistical approaches or predefined assumptions about OOD data distributions, hindering their efficacy in addressing mul…
When and How Does In-Distribution Label Help Out-of-Distribution Detection?
Xuefeng Du, Yiyou Sun, Yixuan Li
Detecting data points deviating from the training distribution is pivotal for ensuring reliable machine learning. Extensive research has been dedicated to the challenge, spanning c…
How Does Unlabeled Data Provably Help Out-of-Distribution Detection?
Xuefeng Du, Zhen Fang, Ilias Diakonikolas +1
Using unlabeled data to regularize the machine learning models has demonstrated promise for improving safety and reliability in detecting out-of-distribution (OOD) data. Harnessing…