研究人员开发了一种新方法，以提高大型语言模型在不同语言中回忆事实的能力。他们创建了一个名为PolyFact的数据集，包含12种语言的10万个事实，用于研究和解决跨语言事实不一致问题。他们的强化学习方法GRPO在提高事实回忆能力和泛化到新语言方面，显著优于标准的微调方法。 AI
影响 通过提高跨语言事实一致性，增强了LLM在多语言应用中的可靠性。
排序理由 该集群包含一篇学术论文，详细介绍了一种改进LLM性能的新方法和数据集。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.06586v1 Announce Type: new Abstract: Large language models (LLMs) trained predominantly on English data encode substantial world knowledge, yet often fail to express it reliably in other languages, a phenomenon known as cross-lingual factual inconsistency. To study and…
Large language models (LLMs) trained predominantly on English data encode substantial world knowledge, yet often fail to express it reliably in other languages, a phenomenon known as cross-lingual factual inconsistency. To study and address this, we introduce PolyFact, a large-sc…