基于大语言模型的因果智能体
Causal Agent based on Large Language Model
AI总结：
该研究针对LLM难以处理因果问题的挑战，提出Causal Agent框架，构建CausalTQA基准，实验显示其在多层级因果问题及真实数据集上性能优于SOTA。
摘要：
大语言模型（LLM）已在多个领域取得显著成功，但因果问题的固有复杂性及因果理论难以用自然语言准确描述，导致LLM难以有效理解和运用因果知识；因果方法不易通过自然语言传达，阻碍LLM准确应用因果知识；此外，因果数据集通常为表格形式，而LLM擅长处理自然语言数据，存在结构不匹配问题，妨碍其对表格数据的有效推理。为解决这些挑战，我们在智能体框架内为LLM配备了因果工具，命名为Causal Agent，使其能处理因果问题。该因果智能体由工具、记忆和推理模块构成：工具模块中，它调用Python代码并使用封装的因果功能模块，实现表格数据与自然语言的对齐；推理模块中，它通过与工具的多次迭代开展推理；记忆模块中，它维护一个字典实例，键为唯一名称，值为因果图。为验证该因果智能体的因果能力，我们构建了Causal Tabular Question Answer（CausalTQA）基准，包含变量级、边级、因果图级、因果效应级四个层级的因果问题，共约1400个问题。实验显示，因果智能体在这四个层级的因果问题上表现出色，准确率均超过80%；在真实世界数据集QRData上验证时，其性能比原始SOTA高出6%。更多见解和实现细节可通过GitHub仓库获取。
英文摘要：
The large language model (LLM) has achieved significant success across various domains. However, the inherent complexity of causal problems and causal theory poses challenges in accurately describing them in natural language, making it difficult for LLM to comprehend and use them effectively. Causal methods are not easily conveyed through natural language, which hinders LLM's ability to apply them accurately. Additionally, causal datasets are typically tabular, while LLM excels in handling natural language data, creating a structural mismatch that impedes effective reasoning with tabular data. To address these challenges, we have equipped the LLM with causal tools within an agent framework, named the Causal Agent, enabling it to tackle causal problems. The causal agent comprises tools, memory, and reasoning modules. In the tool module, the causal agent calls Python code and uses the encapsulated causal function module to align tabular data with natural language. In the reasoning module, the causal agent performs reasoning through multiple iterations with the tools. In the memory module, the causal agent maintains a dictionary instance where the keys are unique names and the values are causal graphs. To verify the causal ability of the causal agent, we established a Causal Tabular Question Answer (CausalTQA) benchmark consisting of four levels of causal problems: variable level, edge level, causal graph level, and causal effect level. CausalTQA consists of about 1.4K for these four levels questions. Causal agent demonstrates remarkable efficacy on the four-level causal problems, with accuracy rates all above 80\%. Through verification on the real-world dataset QRData, the causal agent is 6\% higher than the original SOTA. For further insights and implementation details, our code is accessible via the GitHub repository https://github.com/kairong-han/causal_agent.
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。
