@inproceedings{kamei-etal-2024-detecting,
title = "Detecting Response Generation Not Requiring Factual Judgment",
author = "Kamei, Ryohei and
Shiono, Daiki and
Akama, Reina and
Suzuki, Jun",
editor = "Cao, Yang (Trista) and
Papadimitriou, Isabel and
Ovalle, Anaelia and
Zampieri, Marcos and
Ferraro, Francis and
Swayamdipta, Swabha",
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.13",
doi = "10.18653/v1/2024.naacl-srw.13",
pages = "116--123",
abstract = "With the remarkable development of large language models (LLMs), ensuring the factuality of output has become a challenge.However, having all the contents of the response with given knowledge or facts is not necessarily a good thing in dialogues.This study aimed to achieve both attractiveness and factuality in a dialogue response for which a task was set to predict sentences that do not require factual correctness judgment such as agreeing, or personal opinions/feelings.We created a dataset, dialogue dataset annotated with fact-check-needed label (DDFC), for this task via crowdsourcing, and classification tasks were performed on several models using this dataset.The model with the highest classification accuracy could yield about 88{\%} accurate classification results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kamei-etal-2024-detecting">
<titleInfo>
<title>Detecting Response Generation Not Requiring Factual Judgment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryohei</namePart>
<namePart type="family">Kamei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daiki</namePart>
<namePart type="family">Shiono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reina</namePart>
<namePart type="family">Akama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</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>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Ferraro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</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>With the remarkable development of large language models (LLMs), ensuring the factuality of output has become a challenge.However, having all the contents of the response with given knowledge or facts is not necessarily a good thing in dialogues.This study aimed to achieve both attractiveness and factuality in a dialogue response for which a task was set to predict sentences that do not require factual correctness judgment such as agreeing, or personal opinions/feelings.We created a dataset, dialogue dataset annotated with fact-check-needed label (DDFC), for this task via crowdsourcing, and classification tasks were performed on several models using this dataset.The model with the highest classification accuracy could yield about 88% accurate classification results.</abstract>
<identifier type="citekey">kamei-etal-2024-detecting</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-srw.13</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-srw.13</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>116</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting Response Generation Not Requiring Factual Judgment
%A Kamei, Ryohei
%A Shiono, Daiki
%A Akama, Reina
%A Suzuki, Jun
%Y Cao, Yang (Trista)
%Y Papadimitriou, Isabel
%Y Ovalle, Anaelia
%Y Zampieri, Marcos
%Y Ferraro, Francis
%Y Swayamdipta, Swabha
%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 kamei-etal-2024-detecting
%X With the remarkable development of large language models (LLMs), ensuring the factuality of output has become a challenge.However, having all the contents of the response with given knowledge or facts is not necessarily a good thing in dialogues.This study aimed to achieve both attractiveness and factuality in a dialogue response for which a task was set to predict sentences that do not require factual correctness judgment such as agreeing, or personal opinions/feelings.We created a dataset, dialogue dataset annotated with fact-check-needed label (DDFC), for this task via crowdsourcing, and classification tasks were performed on several models using this dataset.The model with the highest classification accuracy could yield about 88% accurate classification results.
%R 10.18653/v1/2024.naacl-srw.13
%U https://aclanthology.org/2024.naacl-srw.13
%U https://doi.org/10.18653/v1/2024.naacl-srw.13
%P 116-123
Markdown (Informal)
[Detecting Response Generation Not Requiring Factual Judgment](https://aclanthology.org/2024.naacl-srw.13) (Kamei et al., NAACL 2024)
ACL
- Ryohei Kamei, Daiki Shiono, Reina Akama, and Jun Suzuki. 2024. Detecting Response Generation Not Requiring Factual Judgment. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 116–123, Mexico City, Mexico. Association for Computational Linguistics.