利用跨语言表现差异定位大模型中的知识专家。
Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency
- 通过对比不同语言下模型的响应差异，识别关键专家。
- 仅禁用约20个专家，就使40%以上问题回答错误。
- 适合研究模型可解释性与知识定位的研究者。
现代大模型在不同语言间表现出显著的行为差异，例如在某些语言中能准确回忆事实信息，而在其他语言中则不能。本文提出将这种跨语言不一致性作为工具，用于混合专家（MoE）大模型的可解释性分析。我们的知识定位框架通过对比模型在语言成功与失败时的路由行为，识别出对特定知识回答起关键作用的专家组件。方法分两步：首先在多种语言中对复杂事实问题进行提问，生成“成功”和“失败”激活桶；其次对MoE路由器日志进行统计对比分析，定位重要专家。为验证这些专家的必要性，我们禁用它们并重新提问。结果表明，尽管仅禁用约20个专家（总6000个），模型在超过40%的情况下无法正确回答。该方法提供了一种现实且可扩展的知识定位方案，适用于日益复杂的大型语言模型。
原文摘要 · Abstract (English)
Modern LLMs continue to exhibit significant variance in behavior across languages, such as being able to recall factual information in some languages but not others. While typically studied as a problem to be mitigated, in this work, we propose leveraging this cross-lingual inconsistency as a tool for interpretability in mixture-of-experts (MoE) LLMs. Our knowledge localization framework contrasts routing for sets of languages where the model correctly recalls information from languages where it fails. This allows us to isolate model components that play a functional role in answering about a piece of knowledge. Our method proceeds in two stages: (1) querying the model with difficult factual questions across a diverse set of languages to generate "success" and "failure" activation buckets and then (2) applying a statistical contrastive analysis to the MoE router logits to identify experts important for knowledge. To validate the necessity of this small number of experts for answering a knowledge question, we deactivate them and re-ask the question. We find that despite only deactivating about 20 out of 6000 experts, the model no longer answers correctly in over 40% of cases. Generally, this method provides a realistic and scalable knowledge localization approach to address increasingly complex LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。