@inproceedings{liu-etal-2025-large,
title = "Large-Scale Corpus Construction and Retrieval-Augmented Generation for {A}ncient {C}hinese Poetry: New Method and Data Insights",
author = "Liu, Yang and
Lan, Lan and
Cao, Jiahuan and
Cheng, Hiuyi and
Ding, Kai and
Jin, Lianwen",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.46/",
doi = "10.18653/v1/2025.findings-naacl.46",
pages = "779--817",
ISBN = "979-8-89176-195-7",
abstract = "Ancient Chinese Poetry (ACP), a critical aspect of Chinese cultural heritage, presents unique challenges for Large Language Models (LLMs). One of the most pressing challenges is the significant hallucination issues faced by LLMs due to data scarcity and limited ability of general LLMs when dealing with ACP. To address these challenges, this paper constructs the ACP-Corpus, which encompasses 1.1 million ancient poems and 990K related texts, designed to enhance the training and performance of LLMs. Alongside this, we develop the ACP-QA dataset, comprising over 12 million question-answer pairs across 24 task categories, and the ACP-Eval dataset for rigorous evaluation purposes, containing 7,050 entries. Building on this resources, we propose the ACP-RAG framework, a specialized Retrieval-Augmented Generation (RAG) approach that significantly improves the performance of LLMs in the domain of ancient poetry from 49.2{\%} to 89.0{\%}. The ACP-RAG contains five modules of semantic coarse-grained retrieval, semantic fine-grained retrieval, keyword retrieval, keyword matching, and context filtering. Experiments show that ACP-RAG achieves a promising response accuracy of 89.0{\%}, surpassing existing LLMs by a remarkable margin. We believe this work not only advances the capabilities of LLMs in processing ancient Chinese poetry but also contributes to the preservation and innovative development within this rich literary tradition. The datasets and code are available at https://github.com/SCUT-DLVCLab/ACP-RAG."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-large">
<titleInfo>
<title>Large-Scale Corpus Construction and Retrieval-Augmented Generation for Ancient Chinese Poetry: New Method and Data Insights</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lan</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahuan</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiuyi</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lianwen</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Ancient Chinese Poetry (ACP), a critical aspect of Chinese cultural heritage, presents unique challenges for Large Language Models (LLMs). One of the most pressing challenges is the significant hallucination issues faced by LLMs due to data scarcity and limited ability of general LLMs when dealing with ACP. To address these challenges, this paper constructs the ACP-Corpus, which encompasses 1.1 million ancient poems and 990K related texts, designed to enhance the training and performance of LLMs. Alongside this, we develop the ACP-QA dataset, comprising over 12 million question-answer pairs across 24 task categories, and the ACP-Eval dataset for rigorous evaluation purposes, containing 7,050 entries. Building on this resources, we propose the ACP-RAG framework, a specialized Retrieval-Augmented Generation (RAG) approach that significantly improves the performance of LLMs in the domain of ancient poetry from 49.2% to 89.0%. The ACP-RAG contains five modules of semantic coarse-grained retrieval, semantic fine-grained retrieval, keyword retrieval, keyword matching, and context filtering. Experiments show that ACP-RAG achieves a promising response accuracy of 89.0%, surpassing existing LLMs by a remarkable margin. We believe this work not only advances the capabilities of LLMs in processing ancient Chinese poetry but also contributes to the preservation and innovative development within this rich literary tradition. The datasets and code are available at https://github.com/SCUT-DLVCLab/ACP-RAG.</abstract>
<identifier type="citekey">liu-etal-2025-large</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.46</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.46/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>779</start>
<end>817</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large-Scale Corpus Construction and Retrieval-Augmented Generation for Ancient Chinese Poetry: New Method and Data Insights
%A Liu, Yang
%A Lan, Lan
%A Cao, Jiahuan
%A Cheng, Hiuyi
%A Ding, Kai
%A Jin, Lianwen
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F liu-etal-2025-large
%X Ancient Chinese Poetry (ACP), a critical aspect of Chinese cultural heritage, presents unique challenges for Large Language Models (LLMs). One of the most pressing challenges is the significant hallucination issues faced by LLMs due to data scarcity and limited ability of general LLMs when dealing with ACP. To address these challenges, this paper constructs the ACP-Corpus, which encompasses 1.1 million ancient poems and 990K related texts, designed to enhance the training and performance of LLMs. Alongside this, we develop the ACP-QA dataset, comprising over 12 million question-answer pairs across 24 task categories, and the ACP-Eval dataset for rigorous evaluation purposes, containing 7,050 entries. Building on this resources, we propose the ACP-RAG framework, a specialized Retrieval-Augmented Generation (RAG) approach that significantly improves the performance of LLMs in the domain of ancient poetry from 49.2% to 89.0%. The ACP-RAG contains five modules of semantic coarse-grained retrieval, semantic fine-grained retrieval, keyword retrieval, keyword matching, and context filtering. Experiments show that ACP-RAG achieves a promising response accuracy of 89.0%, surpassing existing LLMs by a remarkable margin. We believe this work not only advances the capabilities of LLMs in processing ancient Chinese poetry but also contributes to the preservation and innovative development within this rich literary tradition. The datasets and code are available at https://github.com/SCUT-DLVCLab/ACP-RAG.
%R 10.18653/v1/2025.findings-naacl.46
%U https://aclanthology.org/2025.findings-naacl.46/
%U https://doi.org/10.18653/v1/2025.findings-naacl.46
%P 779-817
Markdown (Informal)
[Large-Scale Corpus Construction and Retrieval-Augmented Generation for Ancient Chinese Poetry: New Method and Data Insights](https://aclanthology.org/2025.findings-naacl.46/) (Liu et al., Findings 2025)
ACL