LLM-as-a-Judge for Reference-less Automatic Code Validation and Refinement for Natural Language to Bash in IT Automation
This addresses the need for reliable reference-less validation of generated Bash code in IT automation, though it appears incremental as it builds on existing LLM-as-a-Judge approaches.
The paper tackled the problem of automatically evaluating and improving code quality for natural language to Bash generation in IT automation by enhancing LLM-as-a-Judge with bidirectional functionality matching and logic representation, achieving up to 8% higher accuracy over baseline and up to 24% improvement in code refinement.
In an effort to automatically evaluate and select the best model and improve code quality for automatic incident remediation in IT Automation, it is crucial to verify if the generated code for remediation action is syntactically and semantically correct and whether it can be executed correctly as intended. There are three approaches: 1) conventional methods use surface form similarity metrics (token match, exact match, etc.) which have numerous limitations, 2) execution-based evaluation focuses more on code functionality based on pass/fail judgments for given test-cases, and 3) LLM-as-a-Judge employs LLMs for automated evaluation to judge if it is a correct answer for a given problem based on pre-defined metrics. In this work, we focused on enhancing LLM-as-a-Judge using bidirectional functionality matching and logic representation for reference-less automatic validation and refinement for Bash code generation to select the best model for automatic incident remediation in IT Automation. We used execution-based evaluation as ground-truth to evaluate our LLM-as-a-Judge metrics. Results show high accuracy and agreement with execution-based evaluation (and up to 8% over baseline). Finally, we built Reflection code agents to utilize judgments and feedback from our evaluation metrics which achieved significant improvement (up to 24% increase in accuracy) for automatic code refinement.