GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910161596055552 |
|---|---|
| author | Choudhury, Nitin Maurya, Bikrant Bikram Pratap Kuwar, Bhavinkumar Vinodbhai Buduru, Arun Balaji |
| author_facet | Choudhury, Nitin Maurya, Bikrant Bikram Pratap Kuwar, Bhavinkumar Vinodbhai Buduru, Arun Balaji |
| contents | Large Language Models (LLMs) trained on massive code corpora are now increasingly capable of generating code that is hard to distinguish from human-written code. This raises practical concerns, including security vulnerabilities and licensing ambiguity, and also motivates a forensic question: 'Who (or which LLM) wrote this piece of code?' We present GoCoMA, a multimodal framework that models an extrinsic hierarchy between (i) code stylometry, capturing higher-level structural and stylistic signatures, and (ii) image representations of binary pre-executable artifacts (BPEA), capturing lower-level, execution-oriented byte semantics shaped by compilation and toolchains. GoCoMA projects modality embeddings into a hyperbolic Poincaré ball, fuses them via a geodesic-cosine similarity-based cross-modal attention (GCSA) fusion mechanism, and back-projects the fused representation to Euclidean space for final LLM-source attribution. Experiments on two open-source benchmarks (CoDET-M4 and LLMAuthorBench) show that GoCoMA consistently outperforms unimodal and Euclidean multimodal baselines under identical evaluation protocols. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16377 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution Choudhury, Nitin Maurya, Bikrant Bikram Pratap Kuwar, Bhavinkumar Vinodbhai Buduru, Arun Balaji Computation and Language Computers and Society Large Language Models (LLMs) trained on massive code corpora are now increasingly capable of generating code that is hard to distinguish from human-written code. This raises practical concerns, including security vulnerabilities and licensing ambiguity, and also motivates a forensic question: 'Who (or which LLM) wrote this piece of code?' We present GoCoMA, a multimodal framework that models an extrinsic hierarchy between (i) code stylometry, capturing higher-level structural and stylistic signatures, and (ii) image representations of binary pre-executable artifacts (BPEA), capturing lower-level, execution-oriented byte semantics shaped by compilation and toolchains. GoCoMA projects modality embeddings into a hyperbolic Poincaré ball, fuses them via a geodesic-cosine similarity-based cross-modal attention (GCSA) fusion mechanism, and back-projects the fused representation to Euclidean space for final LLM-source attribution. Experiments on two open-source benchmarks (CoDET-M4 and LLMAuthorBench) show that GoCoMA consistently outperforms unimodal and Euclidean multimodal baselines under identical evaluation protocols. |
| title | GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution |
| topic | Computation and Language Computers and Society |
| url | https://arxiv.org/abs/2604.16377 |