Fine-tuned models outperform LLMs in multilingual fact-checking

Researchers have developed a multilingual fact-checking system for Factiverse, utilizing fine-tuned compact models for efficiency and scalability. The system employs a three-stage pipeline involving claim detection, evidence retrieval, and veracity prediction. Comparative experiments showed that fine-tuned models like XLM-RoBERTa-Large and mmBERT-base offer strong performance across numerous languages, remaining competitive with larger LLMs such as GPT-5.2 and Claude Opus 4.6 in terms of accuracy and significantly outperforming them in latency and cost-efficiency for production deployments. AI

IMPACT Demonstrates the viability of smaller, fine-tuned models for efficient, large-scale multilingual AI applications.

RANK_REASON The cluster contains an academic paper detailing a new system and comparative analysis of models for fact-checking. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• Claude Opus 4.6
• Factiverse
• GPT-5.2
• mmBERT-base
• Qwen3-8b
• XLM-RoBERTa-Large

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →