LLaMA based Punctuation Restoration With Forward Pass Only Decoding

This paper introduces two advancements in the field of Large Language Model Annotation with a focus on punctuation restoration tasks. Our first contribution is the application of LLaMA for punctuation restoration, which demonstrates superior performance compared to the established benchmark. Despite...

Full description

Saved in:
Bibliographic Details
Main Authors Pang, Yutong, Paul, Debjyoti, Jiang, Kevin, Zhang, Xuedong, Lei, Xin
Format Journal Article
LanguageEnglish
Published 09.08.2024
Subjects
Computer Science - Computation and Language
Online AccessGet full text

Cover

More Information
Summary:This paper introduces two advancements in the field of Large Language Model Annotation with a focus on punctuation restoration tasks. Our first contribution is the application of LLaMA for punctuation restoration, which demonstrates superior performance compared to the established benchmark. Despite its impressive quality, LLaMA faces challenges regarding inference speed and hallucinations. To address this, our second contribution presents Forward Pass Only Decoding (FPOD), a novel decoding approach for annotation tasks. This innovative method results in a substantial 19.8x improvement in inference speed, effectively addressing a critical bottleneck and enhancing the practical utility of LLaMA for large-scale data annotation tasks without hallucinations. The combination of these contributions not only solidifies LLaMA as a powerful tool for punctuation restoration but also highlights FPOD as a crucial strategy for overcoming speed constraints.
DOI:10.48550/arxiv.2408.11845