@inproceedings{leippert-etal-2024-clarify,
title = "To Clarify or not to Clarify: A Comparative Analysis of Clarification Classification with Fine-Tuning, Prompt Tuning, and Prompt Engineering",
author = "Leippert, Alina and
Anikina, Tatiana and
Kiefer, Bernd and
Genabith, Josef",
editor = "Cao, Yang (Trista) and
Papadimitriou, Isabel and
Ovalle, Anaelia",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-srw.12",
pages = "105--115",
abstract = "Misunderstandings occur all the time in human conversation but deciding on when to ask for clarification is a challenging task for conversational systems that requires a balance between asking too many unnecessary questions and running the risk of providing incorrect information. This work investigates clarification identification based on the task and data from (Xu et al., 2019), reproducing their Transformer baseline and extending it by comparing pre-trained language model fine-tuning, prompt tuning and manual prompt engineering on the task of clarification identification. Our experiments show strong performance with LM and a prompt tuning approach with BERT and RoBERTa, outperforming standard LM fine-tuning, while manual prompt engineering with GPT-3.5 proved to be less effective, although informative prompt instructions have the potential of steering the model towards generating more accurate explanations for why clarification is needed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="leippert-etal-2024-clarify">
<titleInfo>
<title>To Clarify or not to Clarify: A Comparative Analysis of Clarification Classification with Fine-Tuning, Prompt Tuning, and Prompt Engineering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Leippert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Anikina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernd</namePart>
<namePart type="family">Kiefer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Genabith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">(Trista)</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Papadimitriou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaelia</namePart>
<namePart type="family">Ovalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Misunderstandings occur all the time in human conversation but deciding on when to ask for clarification is a challenging task for conversational systems that requires a balance between asking too many unnecessary questions and running the risk of providing incorrect information. This work investigates clarification identification based on the task and data from (Xu et al., 2019), reproducing their Transformer baseline and extending it by comparing pre-trained language model fine-tuning, prompt tuning and manual prompt engineering on the task of clarification identification. Our experiments show strong performance with LM and a prompt tuning approach with BERT and RoBERTa, outperforming standard LM fine-tuning, while manual prompt engineering with GPT-3.5 proved to be less effective, although informative prompt instructions have the potential of steering the model towards generating more accurate explanations for why clarification is needed.</abstract>
<identifier type="citekey">leippert-etal-2024-clarify</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-srw.12</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>105</start>
<end>115</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To Clarify or not to Clarify: A Comparative Analysis of Clarification Classification with Fine-Tuning, Prompt Tuning, and Prompt Engineering
%A Leippert, Alina
%A Anikina, Tatiana
%A Kiefer, Bernd
%A Genabith, Josef
%Y Cao, Yang (Trista)
%Y Papadimitriou, Isabel
%Y Ovalle, Anaelia
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F leippert-etal-2024-clarify
%X Misunderstandings occur all the time in human conversation but deciding on when to ask for clarification is a challenging task for conversational systems that requires a balance between asking too many unnecessary questions and running the risk of providing incorrect information. This work investigates clarification identification based on the task and data from (Xu et al., 2019), reproducing their Transformer baseline and extending it by comparing pre-trained language model fine-tuning, prompt tuning and manual prompt engineering on the task of clarification identification. Our experiments show strong performance with LM and a prompt tuning approach with BERT and RoBERTa, outperforming standard LM fine-tuning, while manual prompt engineering with GPT-3.5 proved to be less effective, although informative prompt instructions have the potential of steering the model towards generating more accurate explanations for why clarification is needed.
%U https://aclanthology.org/2024.naacl-srw.12
%P 105-115
Markdown (Informal)
[To Clarify or not to Clarify: A Comparative Analysis of Clarification Classification with Fine-Tuning, Prompt Tuning, and Prompt Engineering](https://aclanthology.org/2024.naacl-srw.12) (Leippert et al., NAACL 2024)
ACL