CoHalLo: code hallucination localization via probing hidden layer vector
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908740414865408 |
|---|---|
| author | Jia, Nan Sang, Wangchao Lin, Pengfei Chen, Xiangping Huang, Yuan Liu, Yi Li, Mingliang |
| author_facet | Jia, Nan Sang, Wangchao Lin, Pengfei Chen, Xiangping Huang, Yuan Liu, Yi Li, Mingliang |
| contents | The localization of code hallucinations aims to identify specific lines of code containing hallucinations, helping developers to improve the reliability of AI-generated code more efficiently. Although recent studies have adopted several methods to detect code hallucination, most of these approaches remain limited to coarse-grained detection and lack specialized techniques for fine-grained hallucination localization. This study introduces a novel method, called CoHalLo, which achieves line-level code hallucination localization by probing the hidden-layer vectors from hallucination detection models. CoHalLo uncovers the key syntactic information driving the model's hallucination judgments and locates the hallucinating code lines accordingly. Specifically, we first fine-tune the hallucination detection model on manually annotated datasets to ensure that it learns features pertinent to code syntactic information. Subsequently, we designed a probe network that projects high-dimensional latent vectors onto a low-dimensional syntactic subspace, generating vector tuples and reconstructing the predicted abstract syntax tree (P-AST). By comparing P-AST with the original abstract syntax tree (O-AST) extracted from the input AI-generated code, we identify the key syntactic structures associated with hallucinations. This information is then used to pinpoint hallucinated code lines. To evaluate CoHalLo's performance, we manually collected a dataset of code hallucinations. The experimental results show that CoHalLo achieves a Top-1 accuracy of 0.4253, Top-3 accuracy of 0.6149, Top-5 accuracy of 0.7356, Top-10 accuracy of 0.8333, IFA of 5.73, Recall@1% Effort of 0.052721, and Effort@20% Recall of 0.155269, which outperforms the baseline methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_24183 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoHalLo: code hallucination localization via probing hidden layer vector Jia, Nan Sang, Wangchao Lin, Pengfei Chen, Xiangping Huang, Yuan Liu, Yi Li, Mingliang Software Engineering The localization of code hallucinations aims to identify specific lines of code containing hallucinations, helping developers to improve the reliability of AI-generated code more efficiently. Although recent studies have adopted several methods to detect code hallucination, most of these approaches remain limited to coarse-grained detection and lack specialized techniques for fine-grained hallucination localization. This study introduces a novel method, called CoHalLo, which achieves line-level code hallucination localization by probing the hidden-layer vectors from hallucination detection models. CoHalLo uncovers the key syntactic information driving the model's hallucination judgments and locates the hallucinating code lines accordingly. Specifically, we first fine-tune the hallucination detection model on manually annotated datasets to ensure that it learns features pertinent to code syntactic information. Subsequently, we designed a probe network that projects high-dimensional latent vectors onto a low-dimensional syntactic subspace, generating vector tuples and reconstructing the predicted abstract syntax tree (P-AST). By comparing P-AST with the original abstract syntax tree (O-AST) extracted from the input AI-generated code, we identify the key syntactic structures associated with hallucinations. This information is then used to pinpoint hallucinated code lines. To evaluate CoHalLo's performance, we manually collected a dataset of code hallucinations. The experimental results show that CoHalLo achieves a Top-1 accuracy of 0.4253, Top-3 accuracy of 0.6149, Top-5 accuracy of 0.7356, Top-10 accuracy of 0.8333, IFA of 5.73, Recall@1% Effort of 0.052721, and Effort@20% Recall of 0.155269, which outperforms the baseline methods. |
| title | CoHalLo: code hallucination localization via probing hidden layer vector |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2512.24183 |