通过多语言平均分离大模型中的概念语义，提升可解释性。
Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
- 用稀疏自编码器提取多语言文本的概念激活，再求平均。
- 多语言平均后概念关联与本体映射相关性显著高于单语言。
- 适合研究模型内部表征、知识推理与可解释性的学者。
将大语言模型与形式化知识表示和推理结合，是解决其缺陷的有前景方向。嵌入与稀疏自编码器广泛用于文本表征，但语义常与语法及语言特异性信息纠缠。本文提出一种方法：通过稀疏自编码器提取概念激活，并在多语言（英语、法语、中文）间平均，以分离概念语义。我们基于OWL本体类创建英文文本，翻译为法语和中文，输入Gemma 2B模型。利用Gemma Scope稀疏自编码器套件获取各语言版本的类激活值，计算多语言平均概念向量，并与本体类间的已知关系进行相关性对比。结果显示，多语言平均后的概念向量比单一语言更接近真实本体关系。这表明该方法能更准确地机械解读模型内部状态，是一种新的高精度解释技术。
原文摘要 · Abstract (English)
Connecting LLMs with formal knowledge representation and reasoning is a promising approach to address their shortcomings. Embeddings and sparse autoencoders are widely used to represent textual content, but the semantics are entangled with syntactic and language-specific information. We propose a method that isolates concept semantics in Large Langue Models by averaging concept activations derived via Sparse Autoencoders. We create English text representations from OWL ontology classes, translate the English into French and Chinese and then pass these texts as prompts to the Gemma 2B LLM. Using the open source Gemma Scope suite of Sparse Autoencoders, we obtain concept activations for each class and language version. We average the different language activations to derive a conceptual average. We then correlate the conceptual averages with a ground truth mapping between ontology classes. Our results give a strong indication that the conceptual average aligns to the true relationship between classes when compared with a single language by itself. The result hints at a new technique which enables mechanistic interpretation of internal network states with higher accuracy.
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。