The Struggles of LLMs in Cross-lingual Code Clone Detection

TL;DR

This paper evaluates the effectiveness of Large Language Models and embedding models in cross-lingual code clone detection, revealing that embedding models outperform LLMs in accuracy, especially on complex code examples.

Contribution

It provides a comprehensive comparison of LLMs and embedding models for cross-lingual code clone detection, highlighting the superior performance of embedding-based representations.

Findings

LLMs achieve high F1 scores (~0.99) on simple code examples.

Embedding models outperform LLMs by 1-20 percentage points on benchmark datasets.

Embedding representations enable more accurate classification of code clones across languages.

Abstract

With the involvement of multiple programming languages in modern software development, cross-lingual code clone detection has gained traction within the software engineering community. Numerous studies have explored this topic, proposing various promising approaches. Inspired by the significant advances in machine learning in recent years, particularly Large Language Models (LLMs), which have demonstrated their ability to tackle various tasks, this paper revisits cross-lingual code clone detection. We evaluate the performance of five (05) LLMs and eight prompts (08) for the identification of cross-lingual code clones. Additionally, we compare these results against two baseline methods. Finally, we evaluate a pre-trained embedding model to assess the effectiveness of the generated representations for classifying clone and non-clone pairs. The studies involving LLMs and Embedding models are evaluated using two widely used cross-lingual datasets, XLCoST and CodeNet. Our results show that LLMs can achieve high F1 scores, up to 0.99, for straightforward programming examples. However, they not only perform less well on programs associated with complex programming challenges but also do not necessarily understand the meaning of "code clones" in a cross-lingual setting. We show that embedding models used to represent code fragments from different programming languages in the same representation space enable the training of a basic classifier that outperforms all LLMs by ~1 and ~20 percentage points on the XLCoST and CodeNet datasets, respectively. This finding suggests that, despite the apparent capabilities of LLMs, embeddings provided by embedding models offer suitable representations to achieve state-of-the-art performance in cross-lingual code clone detection.