Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thulke, David, Gao, Yingbo, Jalota, Rricha, Dugast, Christian, Ney, Hermann
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914987196284928
author Thulke, David
Gao, Yingbo
Jalota, Rricha
Dugast, Christian
Ney, Hermann
author_facet Thulke, David
Gao, Yingbo
Jalota, Rricha
Dugast, Christian
Ney, Hermann
contents This paper explores the rapid development of a telephone call summarization system utilizing large language models (LLMs). Our approach involves initial experiments with prompting existing LLMs to generate summaries of telephone conversations, followed by the creation of a tailored synthetic training dataset utilizing stronger frontier models. We place special focus on the diversity of the generated data and on the ability to control the length of the generated summaries to meet various use-case specific requirements. The effectiveness of our method is evaluated using two state-of-the-art LLM-as-a-judge-based evaluation techniques to ensure the quality and relevance of the summaries. Our results show that fine-tuned Llama-2-7B-based summarization model performs on-par with GPT-4 in terms of factual accuracy, completeness and conciseness. Our findings demonstrate the potential for quickly bootstrapping a practical and efficient call summarization system.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18624
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization
Thulke, David
Gao, Yingbo
Jalota, Rricha
Dugast, Christian
Ney, Hermann
Computation and Language
Artificial Intelligence
Machine Learning
This paper explores the rapid development of a telephone call summarization system utilizing large language models (LLMs). Our approach involves initial experiments with prompting existing LLMs to generate summaries of telephone conversations, followed by the creation of a tailored synthetic training dataset utilizing stronger frontier models. We place special focus on the diversity of the generated data and on the ability to control the length of the generated summaries to meet various use-case specific requirements. The effectiveness of our method is evaluated using two state-of-the-art LLM-as-a-judge-based evaluation techniques to ensure the quality and relevance of the summaries. Our results show that fine-tuned Llama-2-7B-based summarization model performs on-par with GPT-4 in terms of factual accuracy, completeness and conciseness. Our findings demonstrate the potential for quickly bootstrapping a practical and efficient call summarization system.
title Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2410.18624