Team QUST at SemEval-2025 Task 10: Evaluating Large Language Models in Multiclass Multi-label Classification of News Entity Framing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jiyan, Liu, Youzheng, Wang, Taihang, Xu, Xiaoman, Wang, Yimin, Jiang, Ye
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918072169791488
author Liu, Jiyan
Liu, Youzheng
Wang, Taihang
Xu, Xiaoman
Wang, Yimin
Jiang, Ye
author_facet Liu, Jiyan
Liu, Youzheng
Wang, Taihang
Xu, Xiaoman
Wang, Yimin
Jiang, Ye
contents This paper describes the participation of QUST_NLP in the SemEval-2025 Task 7. We propose a three-stage retrieval framework specifically designed for fact-checked claim retrieval. Initially, we evaluate the performance of several retrieval models and select the one that yields the best results for candidate retrieval. Next, we employ multiple re-ranking models to enhance the candidate results, with each model selecting the Top-10 outcomes. In the final stage, we utilize weighted voting to determine the final retrieval outcomes. Our approach achieved 5th place in the monolingual track and 7th place in the crosslingual track. We release our system code at: https://github.com/warmth27/SemEval2025_Task7.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21564
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Team QUST at SemEval-2025 Task 10: Evaluating Large Language Models in Multiclass Multi-label Classification of News Entity Framing
Liu, Jiyan
Liu, Youzheng
Wang, Taihang
Xu, Xiaoman
Wang, Yimin
Jiang, Ye
Computation and Language
Artificial Intelligence
This paper describes the participation of QUST_NLP in the SemEval-2025 Task 7. We propose a three-stage retrieval framework specifically designed for fact-checked claim retrieval. Initially, we evaluate the performance of several retrieval models and select the one that yields the best results for candidate retrieval. Next, we employ multiple re-ranking models to enhance the candidate results, with each model selecting the Top-10 outcomes. In the final stage, we utilize weighted voting to determine the final retrieval outcomes. Our approach achieved 5th place in the monolingual track and 7th place in the crosslingual track. We release our system code at: https://github.com/warmth27/SemEval2025_Task7.
title Team QUST at SemEval-2025 Task 10: Evaluating Large Language Models in Multiclass Multi-label Classification of News Entity Framing
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.21564