NatLan：原生语言提示通过语言触发提供和领域触发保留促进知识抽取
NatLan: Native Language Prompting Facilitates Knowledge Elicitation Through Language Trigger Provision and Domain Trigger Retention
AI总结：
本文提出NatLan方法，通过多MLLM协作策略和引入角色增强的领域特定MLLM作为翻译器，在提供语言触发的同时保留领域触发，从而提升多语言大模型在非主导语言问答中的表现。
摘要：
多语言大型语言模型（MLLMs）在非主导语言中回答问题的表现不如在主导语言中的表现。尽管现有的先翻译后回答方法缓解了这一问题，但其有效性背后的机制仍不清楚。在本研究中，我们将MLLMs的主导语言类比为人类的母语，并使用两个人类认知特征：语言触发（LT）和领域触发（DT），来解释先翻译后回答方法背后的机制。这揭示了虽然这些方法提供了充足的LT，但在DT保留方面仍存在不足。为了缓解这一问题，我们提出了原生语言提示（NatLan），采用多MLLM协作策略，并引入一个额外的、具有更强多语言理解能力的角色增强领域特定MLLM作为翻译器。在五个语言问答基准测试中，NatLan实现了高达31.28%的准确率提升，并且与现有的最先进方法相比，在多达87%的案例中提供了相当或更高的DT保留率。我们的代码可在https://github.com/AnonyNLP/NatLan获取。
英文摘要：
Multilingual large language models (MLLMs) do not perform as well when answering questions in non-dominant languages as they do in their dominant languages. Although existing translate-then-answer methods alleviate this issue, the mechanisms behind their effectiveness remain unclear. In this study, we analogize the dominant language of MLLMs to the native language of humans and use two human cognitive features: the Language Trigger (LT) and the Domain Trigger (DT), to interpret the mechanisms behind translate-then-answer methods. This reveals that while sufficient LTs are provided by these methods, there remains a deficiency in DT retention. To mitigate this issue, we propose Native Language Prompting (NatLan), employing a Multi-MLLM collaboration strategy and introducing an additional role-enhanced domain-specific MLLM with stronger multilingual understanding capabilities as the translator. Across five language QA benchmarks, NatLan achieves up to a 31.28% improvement in accuracy and, compared to existing state-of-the-art methods, provides comparable or greater retention of DTs in up to 87% of cases. Our code is available at https://github.com/AnonyNLP/NatLan.
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。
