NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness

By Manav Singhal, Tushar Aggarwal, Abhijeet Awasthi, Nagarajan Natarajan, Aditya Kanade. 2024

31 citations recorded by the source corpus.

Existing evaluation benchmarks of language models of code (code LMs) focus almost exclusively on whether the LMs can generate functionally-correct code. In real-world software engineering, developers think beyond functional correctness. They have requirements on"how"a functionality should be implemented to meet overall system design objectives like efficiency, security, and maintainability. They would also trust the code LMs more if the LMs demonstrate robust understanding of such requirements. We propose a new benchmark NoFunEval to evaluate code LMs on non-functional requirements and simple classification instances for both functional and non-functional requirements. We propose a prompting method, Coding Concepts (CoCo), as a way for a developer to communicate the domain knowledge to the LMs. We conduct an extensive evaluation of 27 code LMs. Our finding is that LMs generally falter when tested on our benchmark, hinting at fundamental blindspots in their training setups. Surprisingly, even the classification accuracy on functional-correctness instances derived from the popular HumanEval benchmark is low, calling in question the depth of their comprehension and the source of their success in generating functionally-correct code in the first place. We release our benchmark and evaluation scripts publicly at https://aka.ms/NoFunEval.

Subfields: Information Systems, Software, Large Language Models, Evaluation & Benchmarks, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Software

In Large Language Models

In Evaluation & Benchmarks

In Code Generation & Program Synthesis

Citations in the corpus

LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code (2024, background): “(Singhal et al., 2024) also propose evaluating LLMs on tasks beyond code generation, but they consider tasks that take into account the non-functional-correctness aspects of programming.”