Abstract:

In this paper, we propose CodeSCM, a Structural Causal Model (SCM) for analyzing multi-modal code generation using large language models (LLMs). By applying interventions to CodeSCM, we measure the causal effects of different prompt modalities, such as natural language, code, and input-output exampl...

Key points:

• Research on large language models
• Engineering application

Source: CodeSCM: Causal Analysis for Multi-Modal Code Generation