DS@GT at CheckThat! 2025: A Simple Retrieval-First, LLM-Backed Framework for Claim Normalization

TL;DR

This paper presents a retrieval-first, LLM-backed framework for claim normalization in multilingual fact-checking, achieving top results in monolingual settings but limited zero-shot performance.

Contribution

The paper introduces a simple, effective retrieval-based approach combined with LLM prompting for claim normalization across multiple languages.

Findings

Achieved first place in 7 out of 13 languages in monolingual tracks.

System performs well with in-dataset retrieval and prompting.

Limited zero-shot generalization observed.

Abstract

Claim normalization is an integral part of any automatic fact-check verification system. It parses the typically noisy claim data, such as social media posts into normalized claims, which are then fed into downstream veracity classification tasks. The CheckThat! 2025 Task 2 focuses specifically on claim normalization and spans 20 languages under monolingual and zero-shot conditions. Our proposed solution consists of a lightweight \emph{retrieval-first, LLM-backed} pipeline, in which we either dynamically prompt a GPT-4o-mini with in-context examples, or retrieve the closest normalization from the train dataset directly. On the official test set, the system ranks near the top for most monolingual tracks, achieving first place in 7 out of of the 13 languages. In contrast, the system underperforms in the zero-shot setting, highlighting the limitation of the proposed solution.