Fei Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fei Liu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Chengyi Wang
Shandong University, School of Computer Science and Technology, Qingdao, China
1 shared publication - Jiahui Dong
Shandong University, School of Computer Science and Technology, Qingdao, China
1 shared publication - Kunwu Zheng
Shandong University, School of Computer Science and Technology, Qingdao, China
1 shared publication - Linhao Wu
Shandong University, School of Computer Science and Technology, Qingdao, China
1 shared publication - Pengyu Xue
Hong Kong Polytechnic University, Hong Kong, Hong Kong
1 shared publication - Xianhang Li
Shandong University, School of Computer Science and Technology, Qingdao, China
1 shared publication
Latest Publications
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 920-942
TransLibEval: Demystify Large Language Models’ Capability in Third-Party Library-Targeted Code Translation
In recent years, Large Language Models (LLMs) have been widely studied in the code translation field on the method, class, and even repository levels. However, most of these benchmarks are limited in terms of Third-Party Library (TPL) categories and scales, making TPL-related errors hard to expose and hindering the development of targeted solutions. Considering the high dependence (over 90%) on TPLs in practical programming, demystifying and analyzing LLMs' code translation performance involving various TPLs becomes imperative. To address this gap, we construct TransLibEval, the first benchmark dedicated to library-centric code translation. It consists of 200 real-world tasks across Python, Java, and C++, each explicitly involving TPLs from diverse categories such as data processing, machine learning, and web development, with comprehensive dependency coverage and high-coverage test suites. We evaluate seven recent LLMs of commercial, general, and code-specialized families under six translation strategies of three categories: Direct, IR-guided, and Retrieval-augmented. Experimental results show a dramatic performance drop compared with library-free settings (average CA decline over 60%), while diverse strategies demonstrate heterogeneous advantages. Furthermore, we analyze 4,831 failed cases from GPT-4o, one of the State-of-the-Art (SOTA) LLMs, revealing numerous third-party reference errors that were obscured previously. These findings highlight the unique challenges of library-centric translation and provide practical guidance for improving TPL-aware code intelligence.
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 920-942
Open AccessTransLibEval: Demystify Large Language Models’ Capability in Third-Party Library-Targeted Code Translation
In recent years, Large Language Models (LLMs) have been widely studied in the code translation field on the method, class, and even repository levels. However, most of these benchmarks are limited in terms of Third-Party Library (TPL) categories and scales, making TPL-related errors hard to expose and hindering the development of targeted solutions. Considering the high dependence (over 90%) on TPLs in practical programming, demystifying and analyzing LLMs' code translation performance involving various TPLs becomes imperative. To address this gap, we construct TransLibEval, the first benchmark dedicated to library-centric code translation. It consists of 200 real-world tasks across Python, Java, and C++, each explicitly involving TPLs from diverse categories such as data processing, machine learning, and web development, with comprehensive dependency coverage and high-coverage test suites. We evaluate seven recent LLMs of commercial, general, and code-specialized families under six translation strategies of three categories: Direct, IR-guided, and Retrieval-augmented. Experimental results show a dramatic performance drop compared with library-free settings (average CA decline over 60%), while diverse strategies demonstrate heterogeneous advantages. Furthermore, we analyze 4,831 failed cases from GPT-4o, one of the State-of-the-Art (SOTA) LLMs, revealing numerous third-party reference errors that were obscured previously. These findings highlight the unique challenges of library-centric translation and provide practical guidance for improving TPL-aware code intelligence.