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

arXiv: https://arxiv.org/abs/2508.17402 · HTML: https://mlsanity.com/paper/2508.17402/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 14 references that are in the map.
- First posted on arXiv 24 Aug 2025.

## Builds on (most cited first, 5 of 5)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Empowering the Fact-checkers! Automatic Identification of Claim Spans on Twitter](https://mlsanity.com/paper/2210.04710/) (2022)
- [From Chaos to Clarity: Claim Normalization to Empower Fact-Checking](https://mlsanity.com/paper/2310.14338/) (2023)
- [The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval](https://mlsanity.com/paper/2503.14828/) (2025)

## Abstract (arXiv)

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 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.