# CodeTD: Topology of Attention Detects Hallucinations in Code LLMs

arXiv: https://arxiv.org/abs/2609.07779 · HTML: https://mlsanity.com/paper/2609.07779/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [An introduction to Topological Data Analysis: fundamental and practical aspects for data scientists](https://mlsanity.com/paper/1710.04019/) (2017)
- [TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space](https://mlsanity.com/paper/2402.17811/) (2024)
- [Do Attention Heads in BERT Track Syntactic Dependencies?](https://mlsanity.com/paper/1911.12246/) (2019)
- [Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation](https://mlsanity.com/paper/2402.09267/) (2024)
- [Artificial Text Detection via Examining the Topology of Attention Maps](https://mlsanity.com/paper/2109.04825/) (2021)
- [Hallucination Detection in LLMs Using Spectral Features of Attention Maps](https://mlsanity.com/paper/2502.17598/) (2025)
- [CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification](https://mlsanity.com/paper/2405.00253/) (2024)
- [Manifold Topology Divergence: a Framework for Comparing Data Manifolds](https://mlsanity.com/paper/2106.04024/) (2021)
- [InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answers](https://mlsanity.com/paper/2403.02889/) (2024)
- [Acceptability Judgements via Examining the Topology of Attention Maps](https://mlsanity.com/paper/2205.09630/) (2022)
- [Hallucination Detection in LLMs with Topological Divergence on Attention Graphs](https://mlsanity.com/paper/2504.10063/) (2025)
- [Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code](https://mlsanity.com/paper/2410.09997/) (2024)
- [Topological Data Analysis for Speech Processing](https://mlsanity.com/paper/2211.17223/) (2022)
- [EyeTrans: Merging Human and Machine Attention for Neural Code Summarization](https://mlsanity.com/paper/2402.14096/) (2024)

## Abstract (arXiv)

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.