@inproceedings{lee-etal-2024-telbench,
title = "{T}el{B}ench: A Benchmark for Evaluating Telco-Specific Large Language Models",
author = "Lee, Sunwoo and
Arya, Dhammiko and
Cho, Seung-Mo and
Han, Gyoung-eun and
Hong, Seokyoung and
Jang, Wonbeom and
Lee, Seojin and
Park, Sohee and
Sek, Sereimony and
Song, Injee and
Yoon, Sungbin and
Davis, Eric",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.45",
pages = "609--626",
abstract = "The telecommunications industry, characterized by its vast customer base and complex service offerings, necessitates a high level of domain expertise and proficiency in customer service center operations. Consequently, there is a growing demand for Large Language Models (LLMs) to augment the capabilities of customer service representatives. This paper introduces a methodology for developing a specialized Telecommunications LLM (Telco LLM) designed to enhance the efficiency of customer service agents and promote consistency in service quality across representatives. We present the construction process of TelBench, a novel dataset created for performance evaluation of customer service expertise in the telecommunications domain. We also evaluate various LLMs and demonstrate the ability to benchmark both proprietary and open-source LLMs on predefined telecommunications-related tasks, thereby establishing metrics that define telcommunications performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2024-telbench">
<titleInfo>
<title>TelBench: A Benchmark for Evaluating Telco-Specific Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunwoo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhammiko</namePart>
<namePart type="family">Arya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Mo</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gyoung-eun</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokyoung</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wonbeom</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seojin</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sohee</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sereimony</namePart>
<namePart type="family">Sek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injee</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungbin</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Davis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoţiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, US</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The telecommunications industry, characterized by its vast customer base and complex service offerings, necessitates a high level of domain expertise and proficiency in customer service center operations. Consequently, there is a growing demand for Large Language Models (LLMs) to augment the capabilities of customer service representatives. This paper introduces a methodology for developing a specialized Telecommunications LLM (Telco LLM) designed to enhance the efficiency of customer service agents and promote consistency in service quality across representatives. We present the construction process of TelBench, a novel dataset created for performance evaluation of customer service expertise in the telecommunications domain. We also evaluate various LLMs and demonstrate the ability to benchmark both proprietary and open-source LLMs on predefined telecommunications-related tasks, thereby establishing metrics that define telcommunications performance.</abstract>
<identifier type="citekey">lee-etal-2024-telbench</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-industry.45</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>609</start>
<end>626</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TelBench: A Benchmark for Evaluating Telco-Specific Large Language Models
%A Lee, Sunwoo
%A Arya, Dhammiko
%A Cho, Seung-Mo
%A Han, Gyoung-eun
%A Hong, Seokyoung
%A Jang, Wonbeom
%A Lee, Seojin
%A Park, Sohee
%A Sek, Sereimony
%A Song, Injee
%A Yoon, Sungbin
%A Davis, Eric
%Y Dernoncourt, Franck
%Y Preoţiuc-Pietro, Daniel
%Y Shimorina, Anastasia
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, US
%F lee-etal-2024-telbench
%X The telecommunications industry, characterized by its vast customer base and complex service offerings, necessitates a high level of domain expertise and proficiency in customer service center operations. Consequently, there is a growing demand for Large Language Models (LLMs) to augment the capabilities of customer service representatives. This paper introduces a methodology for developing a specialized Telecommunications LLM (Telco LLM) designed to enhance the efficiency of customer service agents and promote consistency in service quality across representatives. We present the construction process of TelBench, a novel dataset created for performance evaluation of customer service expertise in the telecommunications domain. We also evaluate various LLMs and demonstrate the ability to benchmark both proprietary and open-source LLMs on predefined telecommunications-related tasks, thereby establishing metrics that define telcommunications performance.
%U https://aclanthology.org/2024.emnlp-industry.45
%P 609-626
Markdown (Informal)
[TelBench: A Benchmark for Evaluating Telco-Specific Large Language Models](https://aclanthology.org/2024.emnlp-industry.45) (Lee et al., EMNLP 2024)
ACL
- Sunwoo Lee, Dhammiko Arya, Seung-Mo Cho, Gyoung-eun Han, Seokyoung Hong, Wonbeom Jang, Seojin Lee, Sohee Park, Sereimony Sek, Injee Song, Sungbin Yoon, and Eric Davis. 2024. TelBench: A Benchmark for Evaluating Telco-Specific Large Language Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 609–626, Miami, Florida, US. Association for Computational Linguistics.