BLBingchang Liu

Bingchang Liu

*This is an algorithmically generated author record based on publicly available information.

Bingchang Liu has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning

    by Bingchang Liu, Chaoyu Chen, Zi Gong, Cong Liao, Huan Wang, Zhichao Lei, Ming Liang, Dajun Chen, Min Shen, Hailian Zhou, et al.

    Code LLMs have emerged as a specialized research field, with remarkable studies dedicated to enhancing model's coding capabilities through fine-tuning on pre-trained models. Previous fine-tuning approaches were typically tailored to specific downstream tasks or scenarios, which meant separate fine-tuning for each task, requiring extensive training resources and posing challenges in terms of deployment and maintenance. Furthermore, these approaches failed to leverage the inherent interconnectedness among different code-related tasks. To overcome these limitations, we present a multi-task fine-tuning framework, MFTCoder, that enables simultaneous and parallel fine-tuning on multiple tasks. By incorporating various loss functions, we effectively address common challenges in multi-task learning, such as data imbalance, varying difficulty levels, and inconsistent convergence speeds. Extensive experiments have conclusively demonstrated that our multi-task fine-tuning approach outperforms both individual fine-tuning on single tasks and fine-tuning on a mixed ensemble of tasks. Moreover, MFTCoder offers efficient training capabilities, including efficient data tokenization modes and parameter efficient fine-tuning (PEFT) techniques, resulting in significantly improved speed compared to traditional fine-tuning methods. MFTCoder seamlessly integrates with several mainstream open-source LLMs, such as CodeLLama and Qwen. Our MFTCoder fine-tuned CodeFuse-DeepSeek-33B claimed the top spot on the Big Code Models Leaderboard ranked by WinRate as of January 30, 2024. MFTCoder is open-sourced at https://github.com/codefuse-ai/MFTCOder


  • Open Access

    MicroFuzz: An Efficient Fuzzing Framework for Microservices

    by Peng Di, Bingchang Liu, Yiyi Gao

    Fuzzing is a widely adopted technique in the software industry to enhance security and software quality. However, most existing fuzzers are specifically designed for monolithic software architectures and face significant limitations when it comes to serving distributed Microservices applications (Apps). These limitations primarily revolve around issues of inconsistency, communication, and applicability which arise due to the differences in monolithic and distributed software architecture. This paper presents a novel fuzzing framework, called Micro-Fuzz, specifically designed for Microservices. Mocking-Assisted Seed Execution, Distributed Tracing, Seed Refresh and Pipeline Parallelism approaches are adopted to address the environmental complexities and dynamics of Microservices and improve the efficiency of fuzzing. MicroFuzz has been successfully implemented and deployed in AntGroup 1, a prominent FinTech company. Its performance has been evaluated in three distinct industrial scenarios: normalized fuzzing, iteration testing, and taint verification. Throughout five months of operation, MicroFuzz has diligently analyzed a substantial codebase, consisting of 261 Apps with over 74.6 million lines of code (LOC). The framework's effectiveness is evident in its detection of 5,718 potential quality or security risks, with 1,764 of them confirmed and fixed as actual security threats by software specialists. Moreover, MicroFuzz significantly increased line coverage by 12.24% and detected new paths by 38.42% in the iteration testing.


  • Open Access

    CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model

    by Peng Di, Jianguo Li, Hang Yu, Wei Jiang, Wenting Cai, Yang Cao, Chaoyu Chen, Dajun Chen, Hongwei Chen, Liang Chen, et al.

    Code Large Language Models (Code LLMs) have gained significant attention in the industry due to their wide applications in the full lifecycle of software engineering. However, the effectiveness of existing models in understanding non-English inputs for multi-lingual code-related tasks is still far from well studied. This paper introduces CodeFuse-13B, an open-sourced pre-trained code LLM 2. It is specifically designed for code-related tasks with both English and Chinese prompts and supports over 40 programming languages. CodeFuse achieves its effectiveness by utilizing a high-quality pre-training dataset that is carefully filtered by program analyzers and optimized during the training process. Extensive experiments are conducted using real-world usage scenarios, the industry-standard benchmark HumanEval-x, and the specially designed CodefuseEval for Chinese prompts. To assess the effectiveness of CodeFuse, we actively collected valuable human feedback from the AntGroup's software development process where CodeFuse has been successfully deployed. The results demonstrate that CodeFuse-13B achieves a HumanEval pass@1 score of 37.10%, positioning it as one of the top multi-lingual code LLMs with similar parameter sizes. In practical scenarios, such as code generation, code translation, code comments, and testcase generation, CodeFuse performs better than other models when confronted with Chinese prompts.