# When Scale Meets Diversity: Evaluating Language Models on Fine-Grained Multilingual Claim Verification

arXiv: https://arxiv.org/abs/2507.20700 · HTML: https://mlsanity.com/paper/2507.20700/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 28 Jul 2025.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [Hypothesis Only Baselines in Natural Language Inference](https://mlsanity.com/paper/1805.01042/) (2018)
- [X-FACT: A New Benchmark Dataset for Multilingual Fact Checking](https://mlsanity.com/paper/2106.09248/) (2021)
- [ConvBERT: Improving BERT with Span-based Dynamic Convolution](https://mlsanity.com/paper/2008.02496/) (2020)
- [FakeCovid -- A Multilingual Cross-domain Fact Check News Dataset for COVID-19](https://mlsanity.com/paper/2006.11343/) (2020)
- [Do Large Language Models Know about Facts?](https://mlsanity.com/paper/2310.05177/) (2023)
- [Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4](https://mlsanity.com/paper/2305.14928/) (2023)
- [MM-COVID: A Multilingual and Multimodal Data Repository for Combating COVID-19 Disinformation](https://mlsanity.com/paper/2011.04088/) (2020)
- [CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking](https://mlsanity.com/paper/2206.11863/) (2022)
- [Multilingual Previously Fact-Checked Claim Retrieval](https://mlsanity.com/paper/2305.07991/) (2023)
- [Claim Verification in the Age of Large Language Models: A Survey](https://mlsanity.com/paper/2408.14317/) (2024)
- [Are Large Language Models Good Fact Checkers: A Preliminary Study](https://mlsanity.com/paper/2311.17355/) (2023)
- [Cross-Lingual Learning vs. Low-Resource Fine-Tuning: A Case Study with Fact-Checking in Turkish](https://mlsanity.com/paper/2403.00411/) (2024)
- [Monolingual and Multilingual Misinformation Detection for Low-Resource Languages: A Comprehensive Survey](https://mlsanity.com/paper/2410.18390/) (2024)

## Built on by (most cited first, 3 of 3)

- [Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models](https://mlsanity.com/paper/2508.03860/) (2025)
- [Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation](https://mlsanity.com/paper/2609.08943/) (2026)
- [Online Language Adaptive Sampling for Better Distributed Cross-lingual Gains](https://mlsanity.com/paper/2609.14969/) (2026)

## Abstract (arXiv)

The rapid spread of multilingual misinformation requires robust automated fact verification systems capable of handling fine-grained veracity assessments across diverse languages. While large language models have shown remarkable capabilities across many NLP tasks, their effectiveness for multilingual claim verification with nuanced classification schemes remains understudied. We conduct a comprehensive evaluation of five state-of-the-art language models on the X-Fact dataset, which spans 25 languages with seven distinct veracity categories. Our experiments compare small language models (encoder-based XLM-R and mT5) with recent decoder-only LLMs (Llama 3.1, Qwen 2.5, Mistral Nemo) using both prompting and fine-tuning approaches. Surprisingly, we find that XLM-R (270M parameters) substantially outperforms all tested LLMs (7-12B parameters), achieving 57.7% macro-F1 compared to the best LLM performance of 16.9%. This represents a 15.8% improvement over the previous state-of-the-art (41.9%), establishing new performance benchmarks for multilingual fact verification. Our analysis reveals problematic patterns in LLM behavior, including systematic difficulties in leveraging evidence and pronounced biases toward frequent categories in imbalanced data settings. These findings suggest that for fine-grained multilingual fact verification, smaller specialized models may be more effective than general-purpose large models, with important implications for practical deployment of fact-checking systems.