Bridging the Gap between User Intent and LLM: A Requirement Alignment Approach for Code Generation

2026-04-17

AI Summary

This work addresses the prevalent issue in large language models (LLMs) where code generation errors often stem from misinterpretations of user requirements. Existing approaches typically assume that LLMs accurately comprehend user intent, thereby overlooking the misalignment between actual requirements and the model’s understanding. To bridge this gap, we propose REA-Coder, the first framework to explicitly integrate a requirement alignment mechanism into the code generation pipeline. REA-Coder operates within a closed-loop iterative process that parses user requirements, detects semantic discrepancies, dynamically refines prompts, and incorporates validation feedback to progressively enhance code output. Extensive experiments across four state-of-the-art LLMs and five standard programming benchmarks demonstrate that REA-Coder consistently outperforms strong baselines, achieving average performance gains ranging from 7.93% to 30.25%, thereby underscoring the critical role of requirement alignment in improving code generation accuracy.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Code generation refers to automatically producing executable programs from user requirements. Recently, researchers have explored approaches to enhance the correctness of generated code with advanced large language models. Although achieving improvements, existing approaches focus on designing reasoning strategies or post-refinement methods to enhance code generation performance. Despite their differences, all these methods share a common assumption: the LLM can correctly understand the given requirement. However, this assumption does not always hold. To fill this gap, we propose REA-Coder, a requirement alignment approach to enhance the code generation performance of LLMs. REA-Coder involves first identifying the requirement content that does not align with LLMs and aligning the requirements. Then, based on the aligned requirements, LLMs generate code and further verify whether the generated code aligns with the requirements, iterating this process of requirement alignment and code generation until generating correct code or achieving the maximum number of iterations. Experimental results show that REA-Coder outperforms all advanced baselines on four LLMs across five programming benchmarks. Concretely, REA-Coder achieves average improvements of 7.93%, 30.25%, 26.75%, 8.59%, and 8.64% on the five benchmark datasets, demonstrating the effectiveness of requirement alignment for improving the code generation performance of LLMs.

Problem

• code generation
• requirement alignment
• large language models
• user intent
• LLM understanding

Innovation

• requirement alignment
• code generation
• large language models
• iterative refinement
• user intent