no code implementations • 2 Dec 2023 • Xunzhu Tang, Zhenghan Chen, Kisub Kim, Haoye Tian, Saad Ezzini, Jacques Klein
To address this pressing issue, we introduce a novel security patch detection system, LLMDA, which capitalizes on Large Language Models (LLMs) and code-text alignment methodologies for patch review, data enhancement, and feature combination.
no code implementations • 24 Apr 2023 • Haoye Tian, Weiqi Lu, Tsz On Li, Xunzhu Tang, Shing-Chi Cheung, Jacques Klein, Tegawendé F. Bissyandé
To assess the feasibility of using an LLM as a useful assistant bot for programmers, we must assess its realistic capabilities on unseen problems as well as its capabilities on various tasks.
1 code implementation • 7 Jan 2023 • Xunzhu Tang, Haoye Tian, Pingfan Kong, Kui Liu, Jacques Klein, Tegawendé F. Bissyande
Our novelty is that we guide the bug finding process by considering that existing bugs have been hinted within app reviews.
1 code implementation • 3 Dec 2022 • Yinghua Li, Xueqi Dang, Haoye Tian, Tiezhu Sun, Zhijie Wang, Lei Ma, Jacques Klein, Tegawende F. Bissyande
In this paper, we conduct the most extensive empirical study on 56, 682 published AI apps from three perspectives: dataset characteristics, development issues, and user feedback and privacy.
1 code implementation • 8 Aug 2022 • Haoye Tian, Xunzhu Tang, Andrew Habib, Shangwen Wang, Kui Liu, Xin Xia, Jacques Klein, Tegawendé F. Bissyandé
To tackle this problem, our intuition is that natural language processing can provide the necessary representations and models for assessing the semantic correlation between a bug (question) and a patch (answer).
1 code implementation • 13 Jun 2022 • Weiguo Pian, Hanyu Peng, Xunzhu Tang, Tiezhu Sun, Haoye Tian, Andrew Habib, Jacques Klein, Tegawendé F. Bissyandé
Representation learning of source code is essential for applying machine learning to software engineering tasks.
1 code implementation • 28 Jul 2021 • Haoye Tian, Yinghua Li, Weiguo Pian, Abdoul Kader Kaboré, Kui Liu, Andrew Habib, Jacques Klein, Tegawendé F. Bissyande
Then, after collecting a large dataset of 1278 plausible patches (written by developers or generated by some 32 APR tools), we use BATS to predict correctness: BATS achieves an AUC between 0. 557 to 0. 718 and a recall between 0. 562 and 0. 854 in identifying correct patches.