Position: Intelligent Coding Systems Should Write Programs with Justifications
This addresses trust issues in AI-driven coding for non-expert users, but it is incremental as it builds on existing justification methods.
The paper argues that intelligent coding systems should generate code with justifications to address trust and usability concerns, proposing neuro-symbolic approaches to ensure cognitive alignment and semantic faithfulness.
Intelligent coding systems are transforming software development by enabling users to specify code behavior in natural language. However, the opaque decision-making of AI-driven coders raises trust and usability concerns, particularly for non-expert users who cannot inspect low-level implementations. We argue that these systems should not only generate code but also produce clear, consistent justifications that bridge model reasoning and user understanding. To this end, we identify two critical justification properties-cognitive alignment and semantic faithfulness-and highlight the limitations of existing methods, including formal verification, static analysis, and post-hoc explainability. We advocate exploring neuro-symbolic approaches for justification generation, where symbolic constraints guide model behavior during training and program semantics are enriched through neural representations, enabling automated consistency checks at inference time.