CIFE: Code Instruction-Following Evaluation
This addresses the need for reliable code generation in real-world deployment by developers, though it is incremental as it builds on existing benchmarks.
The paper tackles the problem of evaluating LLMs for code generation beyond functional correctness by introducing a benchmark with developer-specified constraints, revealing that while strong models achieve over 90% partial adherence, strict adherence remains between 39-66%.
Large Language Models (LLMs) are increasingly applied to real-world code generation, where functional correctness alone is insufficient for reliable deployment, developers also expect adherence to explicit requirements for robustness, formatting, and security. Existing benchmarks primarily assess correctness through test-case execution, offering limited insight into how reliably models follow such constraints. We introduce a benchmark of 1,000 Python tasks, each paired with an average of 7 developer-specified constraints spanning 13 categories. Constraints are curated through a four-stage human-LLM pipeline to ensure they are atomic, relevant, and objective. We evaluate 14 open- and closed-source models using complementary adherence metrics and propose the C2A Score, a composite measure that jointly captures correctness and constraint compliance. Results reveal a substantial gap between partial and strict satisfaction, while strong models achieve over 90% partial adherence, strict adherence remains between 39-66%. These findings highlight that trustworthy code generation requires not only correctness but also consistent adherence to developer intent.