用大模型提炼因果知识，人机协作提升建模效果
Evaluating Large Language Models for Causal Modeling
- 用大模型将领域知识转为因果变量，增强建模视角
- GPT-4-turbo等在变量提炼上优于Mixtral-8x22b
- Mixtral-8x22b更擅长识别交互实体，受领域影响大
本文研究如何将因果领域知识转化为更符合因果数据科学规范的表示。为此，我们提出两项新任务：利用大模型（LLM）提炼因果变量和检测交互实体。实验表明，当前大模型如GPT-4-turbo和Llama3-70b在将领域知识提炼为因果变量方面优于稀疏专家模型Mixtral-8x22b；而后者在识别交互实体方面表现更优。此外，模型性能与生成实体的领域密切相关。
原文摘要 · Abstract (English)
In this paper, we consider the process of transforming causal domain knowledge into a representation that aligns more closely with guidelines from causal data science. To this end, we introduce two novel tasks related to distilling causal domain knowledge into causal variables and detecting interaction entities using LLMs. We have determined that contemporary LLMs are helpful tools for conducting causal modeling tasks in collaboration with human experts, as they can provide a wider perspective. Specifically, LLMs, such as GPT-4-turbo and Llama3-70b, perform better in distilling causal domain knowledge into causal variables compared to sparse expert models, such as Mixtral-8x22b. On the contrary, sparse expert models such as Mixtral-8x22b stand out as the most effective in identifying interaction entities. Finally, we highlight the dependency between the domain where the entities are generated and the performance of the chosen LLM for causal modeling.
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。