@inproceedings{tian-etal-2025-dutir831,
title = "{DUTIR}831 at {S}em{E}val-2025 Task 5: A Multi-Stage {LLM} Approach to {GND} Subject Assignment for {TIBKAT} Records",
author = "Tian, Yicen and
Yu, Erchen and
Wang, Yanan and
Li, Dailin and
Yao, Jiaqi and
Lin, Hongfei and
Zong, Linlin and
Xu, Bo",
editor = "Rosenthal, Sara and
Ros{\'a}, Aiala and
Ghosh, Debanjan and
Zampieri, Marcos",
booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.semeval-1.52/",
pages = "363--372",
ISBN = "979-8-89176-273-2",
abstract = "This paper introduces DUTIR831{'}s approach to SemEval-2025 Task 5, which focuses on generating relevant subjects from the Integrated Authority File (GND) for tagging multilingual technical records in the TIBKAT database. To address challenges in understanding the hierarchical GND taxonomy and automating subject assignment, a three-stage approach is proposed: (1) a data synthesis stage that utilizes LLM to generate and selectively filter high-quality data, (2) a model training module that leverages LLMs and various training strategies to acquire GND knowledge and refine TIBKAT preferences, and (3) a subject terms completion mechanism consisting of multi-sampling ranking, subject terms extraction using a LLM, vector-based model retrieval, and various re-ranking strategies.The quantitative evaluation results show that our system is ranked 2nd in the all-subject datasets and 4th in the tib-core-subjects datasets. And the qualitative evaluation results show that the system is ranked 2nd in the tib-core-subjects datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tian-etal-2025-dutir831">
<titleInfo>
<title>DUTIR831 at SemEval-2025 Task 5: A Multi-Stage LLM Approach to GND Subject Assignment for TIBKAT Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yicen</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erchen</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dailin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaqi</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linlin</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-273-2</identifier>
</relatedItem>
<abstract>This paper introduces DUTIR831’s approach to SemEval-2025 Task 5, which focuses on generating relevant subjects from the Integrated Authority File (GND) for tagging multilingual technical records in the TIBKAT database. To address challenges in understanding the hierarchical GND taxonomy and automating subject assignment, a three-stage approach is proposed: (1) a data synthesis stage that utilizes LLM to generate and selectively filter high-quality data, (2) a model training module that leverages LLMs and various training strategies to acquire GND knowledge and refine TIBKAT preferences, and (3) a subject terms completion mechanism consisting of multi-sampling ranking, subject terms extraction using a LLM, vector-based model retrieval, and various re-ranking strategies.The quantitative evaluation results show that our system is ranked 2nd in the all-subject datasets and 4th in the tib-core-subjects datasets. And the qualitative evaluation results show that the system is ranked 2nd in the tib-core-subjects datasets.</abstract>
<identifier type="citekey">tian-etal-2025-dutir831</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.52/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>363</start>
<end>372</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DUTIR831 at SemEval-2025 Task 5: A Multi-Stage LLM Approach to GND Subject Assignment for TIBKAT Records
%A Tian, Yicen
%A Yu, Erchen
%A Wang, Yanan
%A Li, Dailin
%A Yao, Jiaqi
%A Lin, Hongfei
%A Zong, Linlin
%A Xu, Bo
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F tian-etal-2025-dutir831
%X This paper introduces DUTIR831’s approach to SemEval-2025 Task 5, which focuses on generating relevant subjects from the Integrated Authority File (GND) for tagging multilingual technical records in the TIBKAT database. To address challenges in understanding the hierarchical GND taxonomy and automating subject assignment, a three-stage approach is proposed: (1) a data synthesis stage that utilizes LLM to generate and selectively filter high-quality data, (2) a model training module that leverages LLMs and various training strategies to acquire GND knowledge and refine TIBKAT preferences, and (3) a subject terms completion mechanism consisting of multi-sampling ranking, subject terms extraction using a LLM, vector-based model retrieval, and various re-ranking strategies.The quantitative evaluation results show that our system is ranked 2nd in the all-subject datasets and 4th in the tib-core-subjects datasets. And the qualitative evaluation results show that the system is ranked 2nd in the tib-core-subjects datasets.
%U https://aclanthology.org/2025.semeval-1.52/
%P 363-372
Markdown (Informal)
[DUTIR831 at SemEval-2025 Task 5: A Multi-Stage LLM Approach to GND Subject Assignment for TIBKAT Records](https://aclanthology.org/2025.semeval-1.52/) (Tian et al., SemEval 2025)
ACL
- Yicen Tian, Erchen Yu, Yanan Wang, Dailin Li, Jiaqi Yao, Hongfei Lin, Linlin Zong, and Bo Xu. 2025. DUTIR831 at SemEval-2025 Task 5: A Multi-Stage LLM Approach to GND Subject Assignment for TIBKAT Records. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 363–372, Vienna, Austria. Association for Computational Linguistics.