[Paper] Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs

Published: (June 7, 2026 at 08:33 AM EDT)
2 min read
Source: arXiv

Source: arXiv - 2606.08605v1

Overview

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.

Key Contributions

This paper presents research in the following areas:

  • cs.CL

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.CL.

Authors

  • Pratuat Amatya
  • Vinay Setty

Paper Information

  • arXiv ID: 2606.08605v1
  • Categories: cs.CL
  • Published: June 7, 2026
  • PDF: Download PDF
0 views
Back to Blog

Related posts

Read more »