# AKCIT-FN at CheckThat! 2025: Switching Fine-Tuned SLMs and LLM Prompting for Multilingual Claim Normalization

arXiv: https://arxiv.org/abs/2509.11496 · HTML: https://mlsanity.com/paper/2509.11496/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 15 Sep 2025.

## Builds on (most cited first, 21 of 21)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers](https://mlsanity.com/paper/2012.15828/) (2020)
- [UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining](https://mlsanity.com/paper/2304.09151/) (2023)
- [AraT5: Text-to-Text Transformers for Arabic Language Generation](https://mlsanity.com/paper/2109.12068/) (2021)
- [MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset](https://mlsanity.com/paper/2202.11684/) (2022)
- [Towards Automated Factchecking: Developing an Annotation Schema and Benchmark for Consistent Automated Claim Detection](https://mlsanity.com/paper/1809.08193/) (2018)
- [Overview of CheckThat! 2020: Automatic Identification and Verification of Claims in Social Media](https://mlsanity.com/paper/2007.07997/) (2020)
- [Overview of the CLEF-2018 CheckThat! Lab on Automatic Identification and Verification of Political Claims. Task 1: Check-Worthiness](https://mlsanity.com/paper/1808.05542/) (2018)
- [PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data](https://mlsanity.com/paper/2008.09144/) (2020)
- [Overview of the CLEF--2021 CheckThat! Lab on Detecting Check-Worthy Claims, Previously Fact-Checked Claims, and Fake News](https://mlsanity.com/paper/2109.12987/) (2021)
- [Overview of the CLEF-2019 CheckThat!: Automatic Identification and Verification of Claims](https://mlsanity.com/paper/2109.15118/) (2021)
- [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)
- [Evaluation of Transfer Learning for Polish with a Text-to-Text Model](https://mlsanity.com/paper/2205.08808/) (2022)
- [V=arta: A Large-Scale Headline-Generation Dataset for Indic Languages](https://mlsanity.com/paper/2305.05858/) (2023)
- [ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language](https://mlsanity.com/paper/2406.10806/) (2024)
- [Breaking Language Barriers with MMTweets: Advancing Cross-Lingual Debunked Narrative Retrieval for Fact-Checking](https://mlsanity.com/paper/2308.05680/) (2023)
- [Sequence-to-Sequence Spanish Pre-trained Language Models](https://mlsanity.com/paper/2309.11259/) (2023)

## Abstract (arXiv)

Claim normalization, the transformation of informal social media posts into concise, self-contained statements, is a crucial step in automated fact-checking pipelines. This paper details our submission to the CLEF-2025 CheckThat! Task~2, which challenges systems to perform claim normalization across twenty languages, divided into thirteen supervised (high-resource) and seven zero-shot (no training data) tracks. Our approach, leveraging fine-tuned Small Language Models (SLMs) for supervised languages and Large Language Model (LLM) prompting for zero-shot scenarios, achieved podium positions (top three) in fifteen of the twenty languages. Notably, this included second-place rankings in eight languages, five of which were among the seven designated zero-shot languages, underscoring the effectiveness of our LLM-based zero-shot strategy. For Portuguese, our initial development language, our system achieved an average METEOR score of 0.5290, ranking third. All implementation artifacts, including inference, training, evaluation scripts, and prompt configurations, are publicly available at https://github.com/ju-resplande/checkthat2025_normalization.