Bilal H Fadlallah — accepted AI-conference papers

2024

Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale

Flavio Di Palo, Prateek Singhi, Bilal H Fadlallah

EMNLP 2024main

Large Language Models (LLMs) face significant challenges at inference time due to their high computational demands. To address this, we present Performance-Guided Knowledge Distillation (PGKD), a cost-effective and high-throughput solution for production text classification applications. PGKD utiliz…

Cited by 2 Source ↗PDF ↗Scholar ↗

2023

An Inductive Bias for Tabular Deep Learning

Ege Beyazit, Jonathan Kozaczuk, Bo Li, Vanessa Wallace, Bilal H Fadlallah

NeurIPS 2023poster

Deep learning methods have achieved state-of-the-art performance in most modeling tasks involving images, text and audio, however, they typically underperform tree-based methods on tabular data. In this paper, we hypothesize that a significant contributor to this performance gap is the interaction b…

Cited by 10 Source ↗PDF ↗Scholar ↗