CodeTD: Topology of Attention Detects Hallucinations in Code LLMs

2026-09-07

AI Summary

本文提出CodeTD方法，基于代码生成模型注意力图的拓扑数据分析，自动评估生成代码的正确性，以检测幻觉问题。

Abstract

As AI-code assistant tools become widespread, automatic assessment of the correctness of generated code becomes a significant challenge. Code LLMs are prone to hallucinations, which may lead to code that does not solve the required problem, or even to code with severe security vulnerabilities. In this paper, we introduce CodeTD -- the first approach to pre-execution assessment of code correctness based on topological data analysis (TDA) of Code LLMs'attention maps. Our method quantifies prompt-generation mismatch using topological patterns of attention maps. We carry out experiments with common benchmarks (HumanEval, MBPP, BigCodeBench, MultiPL-E), 5 programming languages and 10 Code LLMs of size up to 34B parameters. The experimental results show that the proposed method outperforms recent baselines. Moreover, CodeTD is transferable between coding benchmarks.

Problem

• AI-code assistant
• code correctness
• hallucinations
• security vulnerabilities

Innovation

• topological data analysis
• attention maps
• pre-execution assessment
• hallucinations detection
• code correctness