@inproceedings{lin-lee-2024-llms,
title = "Can {LLM}s Understand the Implication of Emphasized Sentences in Dialogue?",
author = "Lin, Guan-Ting and
Lee, Hung-yi",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.782",
pages = "13391--13401",
abstract = "Emphasis is a crucial component in human communication, which indicates speaker{'}s intention and implication beyond pure text in dialogue. While Large Language Models (LLMs) have revolutionized natural language processing, their ability to understand emphasis in dialogue remains uncertain. This paper introduces Emphasized-Talk, a benchmark dataset with annotated dialogue samples capturing the implications of emphasis. We evaluate various LLMs, both open-source and commercial, to assess their performance in understanding and generating emphasis. Additionally, we propose an automatic evaluation pipeline using GPT-4, which achieve high correlation with human scoring. Our findings reveal that although commercial LLMs generally perform better, there is still significant room for improvement in comprehending emphasized sentences.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-lee-2024-llms">
<titleInfo>
<title>Can LLMs Understand the Implication of Emphasized Sentences in Dialogue?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guan-Ting</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-yi</namePart>
<namePart type="family">Lee</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>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emphasis is a crucial component in human communication, which indicates speaker’s intention and implication beyond pure text in dialogue. While Large Language Models (LLMs) have revolutionized natural language processing, their ability to understand emphasis in dialogue remains uncertain. This paper introduces Emphasized-Talk, a benchmark dataset with annotated dialogue samples capturing the implications of emphasis. We evaluate various LLMs, both open-source and commercial, to assess their performance in understanding and generating emphasis. Additionally, we propose an automatic evaluation pipeline using GPT-4, which achieve high correlation with human scoring. Our findings reveal that although commercial LLMs generally perform better, there is still significant room for improvement in comprehending emphasized sentences.</abstract>
<identifier type="citekey">lin-lee-2024-llms</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.782</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>13391</start>
<end>13401</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can LLMs Understand the Implication of Emphasized Sentences in Dialogue?
%A Lin, Guan-Ting
%A Lee, Hung-yi
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F lin-lee-2024-llms
%X Emphasis is a crucial component in human communication, which indicates speaker’s intention and implication beyond pure text in dialogue. While Large Language Models (LLMs) have revolutionized natural language processing, their ability to understand emphasis in dialogue remains uncertain. This paper introduces Emphasized-Talk, a benchmark dataset with annotated dialogue samples capturing the implications of emphasis. We evaluate various LLMs, both open-source and commercial, to assess their performance in understanding and generating emphasis. Additionally, we propose an automatic evaluation pipeline using GPT-4, which achieve high correlation with human scoring. Our findings reveal that although commercial LLMs generally perform better, there is still significant room for improvement in comprehending emphasized sentences.
%U https://aclanthology.org/2024.findings-emnlp.782
%P 13391-13401
Markdown (Informal)
[Can LLMs Understand the Implication of Emphasized Sentences in Dialogue?](https://aclanthology.org/2024.findings-emnlp.782) (Lin & Lee, Findings 2024)
ACL