DS@GT at CheckThat! 2025: A Simple Retrieval-First, LLM-Backed Framework for Claim Normalization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909751096377344 |
|---|---|
| author | Pramov, Aleksandar Ma, Jiangqin Patel, Bina |
| author_facet | Pramov, Aleksandar Ma, Jiangqin Patel, Bina |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17402 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DS@GT at CheckThat! 2025: A Simple Retrieval-First, LLM-Backed Framework for Claim Normalization Pramov, Aleksandar Ma, Jiangqin Patel, Bina Computation and Language Information Retrieval 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. |
| title | DS@GT at CheckThat! 2025: A Simple Retrieval-First, LLM-Backed Framework for Claim Normalization |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2508.17402 |