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

TL;DR

This paper presents a three-stage retrieval framework for fact-checked claim retrieval, combining model evaluation, re-ranking, and voting, achieving top rankings in SemEval-2025 Task 7.

Contribution

The paper introduces a novel three-stage retrieval framework tailored for fact-checked claim retrieval, with model evaluation, re-ranking, and voting components.

Findings

Achieved 5th place in monolingual track

Achieved 7th place in crosslingual track

Demonstrated effectiveness of multi-stage retrieval approach

Abstract

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.