2 papers
cs.CL2026
Do LLM hallucination detectors suffer from low-resource effect?
Debtanu Datta, Mohan Kishore Chilukuri, Yash Kumar +2
LLMs, while outperforming humans in a wide range of tasks, can still fail in unanticipated ways. We focus on two pervasive failure modes: (i) hallucinations, where models produce i…
cs.LG2025
Understanding Generalization, Robustness, and Interpretability in Low-Capacity Neural Networks
Yash Kumar
Although modern deep learning often relies on massive over-parameterized models, the fundamental interplay between capacity, sparsity, and robustness in low-capacity networks remai…