Success is in the Details: Evaluate and Enhance Details Sensitivity of Code LLMs through Counterfactuals

TL;DR

This paper introduces a new benchmark and fine-tuning framework to evaluate and improve code LLMs' sensitivity to detail changes, leading to better performance on sensitive tasks.

Contribution

The paper presents CTF-Code, a benchmark for code sensitivity, and CTF-Instruct, a fine-tuning method to enhance LLMs' sensitivity to details in code tasks.

Findings

LLMs experience over 10% performance drop on CTF-Code with detail perturbations.

Fine-tuning with CTF-Instruct data improves LLM performance by over 2% on CTF-Code.

Sensitivity-focused training boosts LLM performance on sensitive code benchmarks.

Abstract

Code Sensitivity refers to the ability of Code LLMs to recognize and respond to details changes in problem descriptions. While current code benchmarks and instruction data focus on difficulty and diversity, sensitivity is overlooked. We first introduce the CTF-Code benchmark, constructed using counterfactual perturbations, minimizing input changes while maximizing output changes. The evaluation shows that many LLMs have a more than 10\% performance drop compared to the original problems. To fully utilize sensitivity, CTF-Instruct, an incremental instruction fine-tuning framework, extends on existing data and uses a selection mechanism to meet the three dimensions of difficulty, diversity, and sensitivity. Experiments show that LLMs fine-tuned with CTF-Instruct data achieve over a 2\% improvement on CTF-Code, and more than a 10\% performance boost on LiveCodeBench, validating the feasibility of enhancing LLMs' sensitivity to improve performance.