GoCoMA fuses code stylometry and binary artifact images via hyperbolic Poincaré ball projection and geodesic-cosine attention to attribute LLM-generated code, outperforming baselines on CoDET-M4 and LLMAuthorBench.
A first look at license compliance capability of llms in code generation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Copy-based reuse creates potential license noncompliance risk in 39.4% of project combinations, with only 2.43% of such reuse detectable via package dependencies.
Vibe coding enables clinicians to prototype digital health tools by prompting LLMs in natural language, democratizing bespoke software development.
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.
citing papers explorer
-
GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution
GoCoMA fuses code stylometry and binary artifact images via hyperbolic Poincaré ball projection and geodesic-cosine attention to attribute LLM-generated code, outperforming baselines on CoDET-M4 and LLMAuthorBench.
-
Ensuring Open Source Integrity: The Intersection of Copy-Based Reuse and License Compliance
Copy-based reuse creates potential license noncompliance risk in 39.4% of project combinations, with only 2.43% of such reuse detectable via package dependencies.
-
Vibe coding for clinicians: democratising bespoke software development for digital health innovation
Vibe coding enables clinicians to prototype digital health tools by prompting LLMs in natural language, democratizing bespoke software development.
-
A Survey on Large Language Models for Code Generation
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.