2 papers
cs.CL2026
Enhancing Hallucination Detection through Noise Injection
Litian Liu, Reza Pourreza, Sunny Panchal +4
Large Language Models (LLMs) are prone to generating plausible yet incorrect responses, known as hallucinations. Effectively detecting hallucinations is therefore crucial for the s…
cs.LG2025
Detecting Out-of-Distribution Through the Lens of Neural Collapse
Litian Liu, Yao Qin
Out-of-Distribution (OOD) detection is critical for safe deployment; however, existing detectors often struggle to generalize across datasets of varying scales and model architectu…