大规模多语言事实核查：微调紧凑模型 vs 大语言模型
Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs
AI总结：
提出一个多语言事实核查系统，通过微调XLM-RoBERTa、mmBERT和SetFit模型，在114种语言的声明检测和28种语言的真实性预测中，与GPT-5.2等LLM相比，展示了紧凑模型的高效和稳定性能。
摘要：
我们提出了一个部署在Factiverse的多语言事实核查系统，旨在跨多种语言实现高吞吐量和低延迟操作。该系统遵循模块化流水线，包含三个阶段：声明检测、证据检索与重排序，以及真实性预测。我们微调了XLM-RoBERTa-Large用于声明检测，mmBERT-base用于三标签立场分类（支持/反驳/混合），以及一个基于SetFit的多语言重排序器用于声明-证据匹配。我们将这些组件与强大的LLM基线进行比较，包括GPT-5.2、Claude Opus~4.6和Qwen3-8b。在涵盖114种语言的声明检测和28种语言的真实性预测的生产数据上的实验表明，任务特定的微调提供了强大且稳定的多语言性能，而微调的检索模型与现代专有嵌入保持竞争力。相同硬件上的延迟测量进一步显示，基于编码器的组件具有巨大的效率提升，支持其在具有严格成本和隐私约束的生产部署中使用。总体而言，紧凑的微调自托管模型仍然是大规模多语言事实核查的实用且有效的基础。本研究的代码和数据可在https://github.com/factiverse/factcheck-editor获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
