# Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs

arXiv: https://arxiv.org/abs/2606.08605 · HTML: https://mlsanity.com/paper/2606.08605/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Builds on (most cited first, 24 of 24)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [Fine-grained Hallucination Detection and Editing for Language Models](https://mlsanity.com/paper/2401.06855/) (2024)
- [AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web](https://mlsanity.com/paper/2305.13117/) (2023)
- [Efficient Few-Shot Learning Without Prompts](https://mlsanity.com/paper/2209.11055/) (2022)
- [DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning](https://mlsanity.com/paper/1809.06416/) (2018)
- [Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers](https://mlsanity.com/paper/2311.09000/) (2023)
- [Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society](https://mlsanity.com/paper/2005.00033/) (2020)
- [A Survey on Natural Language Processing for Fake News Detection](https://mlsanity.com/paper/1811.00770/) (2018)
- [Claim Detection for Automated Fact-checking: A Survey on Monolingual, Multilingual and Cross-Lingual Research](https://mlsanity.com/paper/2401.11969/) (2024)
- [Jointly embedding the local and global relations of heterogeneous graph for rumor detection](https://mlsanity.com/paper/1909.04465/) (2019)
- [The Perils & Promises of Fact-checking with Large Language Models](https://mlsanity.com/paper/2310.13549/) (2023)
- [BRENDA: Browser Extension for Fake News Detection](https://mlsanity.com/paper/2005.13270/) (2020)
- [Generative Large Language Models in Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2407.02351/) (2024)
- [Finding Streams in Knowledge Graphs to Support Fact Checking](https://mlsanity.com/paper/1708.07239/) (2017)
- [Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models](https://mlsanity.com/paper/2402.12147/) (2024)
- [FactCheck Editor: Multilingual Text Editor with End-to-End fact-checking](https://mlsanity.com/paper/2404.19482/) (2024)
- [LiveFC: A System for Live Fact-Checking of Audio Streams](https://mlsanity.com/paper/2408.07448/) (2024)
- [FactIR: A Real-World Zero-shot Open-Domain Retrieval Benchmark for Fact-Checking](https://mlsanity.com/paper/2502.06006/) (2025)
- [ShortCheck: Checkworthiness Detection of Multilingual Short-Form Videos](https://mlsanity.com/paper/2509.20467/) (2025)

## Built on by (most cited first, 1 of 1)

- [Calibrating Small Language Models for Claim Check-Worthiness Detection](https://mlsanity.com/paper/2608.30731/) (2026)

## Abstract (arXiv)

We present a multilingual fact-checking system deployed at Factiverse, designed for high-throughput and low-latency operation across diverse languages. The system follows a modular pipeline with three stages: claim detection, evidence retrieval and re-ranking, and veracity prediction. We fine-tune XLM-RoBERTa-Large for claim detection, mmBERT-base for three-label stance classification (Supports/Refutes/Mixed), and a SetFit-based multilingual re-ranker for claim--evidence matching. We compare these components against strong LLM baselines, including GPT-5.2, Claude Opus~4.6, and Qwen3-8b. Experiments on production data spanning 114 languages for claim detection and 28 languages for veracity prediction show that task-specific fine-tuning provides strong and stable multilingual performance, while the fine-tuned retrieval model remains competitive with modern proprietary embeddings. Same-hardware latency measurements further show large efficiency gains for encoder-based components, supporting their use in production deployments with tight cost and privacy constraints. Overall, compact fine-tuned, self-hosted models remain a practical and effective foundation for multilingual fact-checking at scale. Code and data used for this study are available at https://github.com/factiverse/factcheck-editor.