2 papers
cs.LG2025
Bitwidth-Specific Logarithmic Arithmetic for Future Hardware-Accelerated Training
Hassan Hamad, Yuou Qiu, Peter A. Beerel +1
While advancements in quantization have significantly reduced the computational costs of inference in deep learning, training still predominantly relies on complex floating-point a…
cs.AI2025
ToolCritic: Detecting and Correcting Tool-Use Errors in Dialogue Systems
Hassan Hamad, Yingru Xu, Liang Zhao +2
Tool-augmented large language models (LLMs) are increasingly employed in real-world applications, but tool usage errors still hinder their reliability. We introduce ToolCritic, a d…