@inproceedings{yu-etal-2024-lfed-literary,
title = "{LFED}: A Literary Fiction Evaluation Dataset for Large Language Models",
author = "Yu, Linhao and
Liu, Qun and
Xiong, Deyi",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.915",
pages = "10466--10475",
abstract = "The rapid evolution of large language models (LLMs) has ushered in the need for comprehensive assessments of their performance across various dimensions. In this paper, we propose LFED, a Literary Fiction Evaluation Dataset, which aims to evaluate the capability of LLMs on the long fiction comprehension and reasoning. We collect 95 literary fictions that are either originally written in Chinese or translated into Chinese, covering a wide range of topics across several centuries. We define a question taxonomy with 8 question categories to guide the creation of 1,304 questions. Additionally, we conduct an in-depth analysis to ascertain how specific attributes of literary fictions (e.g., novel types, character numbers, the year of publication) impact LLM performance in evaluations. Through a series of experiments involving various state-of-the-art LLMs, our findings reveal that these models face considerable challenges in effectively addressing questions related to literary fictions, with ChatGPT reaching only 57.08{\%} under the zero-shot setting. The dataset will be publicly available at https://github.com/tjunlp-lab/LFED.git.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2024-lfed-literary">
<titleInfo>
<title>LFED: A Literary Fiction Evaluation Dataset for Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Linhao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rapid evolution of large language models (LLMs) has ushered in the need for comprehensive assessments of their performance across various dimensions. In this paper, we propose LFED, a Literary Fiction Evaluation Dataset, which aims to evaluate the capability of LLMs on the long fiction comprehension and reasoning. We collect 95 literary fictions that are either originally written in Chinese or translated into Chinese, covering a wide range of topics across several centuries. We define a question taxonomy with 8 question categories to guide the creation of 1,304 questions. Additionally, we conduct an in-depth analysis to ascertain how specific attributes of literary fictions (e.g., novel types, character numbers, the year of publication) impact LLM performance in evaluations. Through a series of experiments involving various state-of-the-art LLMs, our findings reveal that these models face considerable challenges in effectively addressing questions related to literary fictions, with ChatGPT reaching only 57.08% under the zero-shot setting. The dataset will be publicly available at https://github.com/tjunlp-lab/LFED.git.</abstract>
<identifier type="citekey">yu-etal-2024-lfed-literary</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.915</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10466</start>
<end>10475</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LFED: A Literary Fiction Evaluation Dataset for Large Language Models
%A Yu, Linhao
%A Liu, Qun
%A Xiong, Deyi
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F yu-etal-2024-lfed-literary
%X The rapid evolution of large language models (LLMs) has ushered in the need for comprehensive assessments of their performance across various dimensions. In this paper, we propose LFED, a Literary Fiction Evaluation Dataset, which aims to evaluate the capability of LLMs on the long fiction comprehension and reasoning. We collect 95 literary fictions that are either originally written in Chinese or translated into Chinese, covering a wide range of topics across several centuries. We define a question taxonomy with 8 question categories to guide the creation of 1,304 questions. Additionally, we conduct an in-depth analysis to ascertain how specific attributes of literary fictions (e.g., novel types, character numbers, the year of publication) impact LLM performance in evaluations. Through a series of experiments involving various state-of-the-art LLMs, our findings reveal that these models face considerable challenges in effectively addressing questions related to literary fictions, with ChatGPT reaching only 57.08% under the zero-shot setting. The dataset will be publicly available at https://github.com/tjunlp-lab/LFED.git.
%U https://aclanthology.org/2024.lrec-main.915
%P 10466-10475
Markdown (Informal)
[LFED: A Literary Fiction Evaluation Dataset for Large Language Models](https://aclanthology.org/2024.lrec-main.915) (Yu et al., LREC-COLING 2024)
ACL