Automated Dialogue Order Processing using Small Large Language Models

Sudhan, Adithya and Shahidi, Reza and Fiech, Adrian (2024) Automated Dialogue Order Processing using Small Large Language Models. In: 33rd Annual Newfoundland Electrical and Computer Engineering Conference (NECEC), November 14, 2024, St. John's, Newfoundland and Labrador.

[img] [English] PDF - Published Version
Available under License Creative Commons Attribution Non-commercial.

Download (730kB)

Abstract

This paper addresses the underexplored intersection of prompt engineering techniques and system design in the context of small Large Language Models (LLMs) aimed at generating structured outputs. While prior studies have largely focused on larger LLMs, the potential of smaller models, which operate with significantly fewer parameters, remains largely untapped, particularly concerning entity extraction in real world task-oriented dialogues. We propose a framework for deploying small LLMs in private, resource-efficient environments to enhance task-oriented workflows. Utilizing the TaskMaster-1 (TM-1-2019) dataset, our research demonstrates how structured outputs can be generated effectively in the absence of any fine-tuning. We evaluate various small LLMs and analyze critical metrics such as validity to identify the key factors and components necessary for transforming dialogue into actionable entities within programming environments.

Item Type: Conference or Workshop Item (Paper)
URI: http://research.library.mun.ca/id/eprint/16961
Item ID: 16961
Keywords: Large Language Models, small-scale LLMs, automated dialogue processing, order placement, prompt engineering
Department(s): Science, Faculty of > Computer Science
Engineering and Applied Science, Faculty of
Date: 14 November 2024
Date Type: Completion
Related URLs:

Actions (login required)

View Item View Item

Downloads

Downloads per month over the past year

View more statistics