2 papers
cs.CL2025
When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs
Shaowen Wang, Yiqi Dong, Ruinian Chang +4
Despite substantial advances, large language models (LLMs) continue to exhibit hallucinations, generating plausible yet incorrect responses. In this paper, we highlight a critical…
cs.LG2025
Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
Binghui Li, Zhixuan Pan, Kaifeng Lyu +1
In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contribut…