Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation

TL;DR

This paper introduces SpecFix, an automated approach to repairing ambiguous natural language descriptions in code generation tasks, significantly improving LLM performance by reducing ambiguity without human intervention.

Contribution

It presents a novel two-step method combining program analysis and contrastive inference to repair ambiguous descriptions for better code generation with LLMs.

Findings

43.58% of descriptions were modified by SpecFix

Pass@1 improved by 30.9% on modified descriptions

Overall benchmark performance increased by 4.09%

Abstract

The growing use of large language models (LLMs) has increased the importance of natural language (NL) in software engineering. However, ambiguity of NL can harm software quality, as unclear problem descriptions may lead to incorrect program generation. Detecting and resolving such ambiguity is challenging, motivating our introduction of the automated repair of ambiguous NL descriptions, which we approach by reducing code generation uncertainty and better aligning NL with input-output examples. Ambiguity repair is difficult for LLMs because they must understand how their interpretation of a description changes when the text is altered. We find that directly prompting LLMs to clarify ambiguity often produces irrelevant or inconsistent edits. To address this, we decompose this task into two simpler steps: (1) analyzing and repairing the LLM's interpretation of the description - captured by the distribution of programs it induces - using traditional testing and program repair, and (2) refining the description based on distribution changes via a method we call contrastive specification inference. We implement this approach in a tool called SpecFix and evaluate it using four state-of-the-art LLMs (GPT-4o, GPT-4o-mini, DeepSeek-V3, and Qwen2.5-Coder-32B-Instruct) on three popular code generation benchmarks (HumanEval+, MBPP+ and LiveCodeBench). Without human intervention or external information, SpecFix modified 43.58% of descriptions, improving Pass@1 on the modified set by 30.9%. This yields a 4.09% absolute improvement across the entire benchmark. Repairs also transfer across models: descriptions repaired for one model improve other models' performance by 10.48%.