Xiao Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiao Yu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Jacky Keung
City University of Hong Kong, Hong Kong, Hong Kong
4 shared publications - Fengji Zhang
City University of Hong Kong
2 shared publications - Hongyi Lin
School of Computer Science and Technology, Shandong University, Qingdao, China
2 shared publications - Pak Yuen Patrick Chan
Department of Computer Science, City University of Hong Kong, Hong Kong, China
2 shared publications - Shuo Liu
City University of Hong Kong, Hong Kong, Hong Kong
2 shared publications - Xin Xia
The State Key Laboratory of Blockchain and Data Security, Zhejiang University, China and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, China
2 shared publications
Latest Publications
- Open Access
- 25 February 2026
- Published by Springer Nature in Empirical Software Engineering
- Vol. 31 (4) , 84
R$^2$ComSync: improving code-comment synchronization with in-context learning and rerankingCode-Comment Synchronization (CCS) aims to synchronize the comments with code changes in an automated fashion, thereby significantly reducing the workload of developers during software maintenance and evolution. While previous studies have proposed various solutions that have shown success, they often exhibit limitations, such as a lack of generalization ability or the need for extensive task-specific learning resources. This motivates us to investigate the potential of Large Language Models (LLMs) in this area. However, a pilot analysis proves that LLMs fall short of State-Of-The-Art (SOTA) CCS approaches because (1) they lack instructive demonstrations for In-Context Learning (ICL) and (2) many correct-prone candidates are not prioritized. To tackle the above challenges, we propose R $$^2$$ ComSync , an ICL-based code- Com ment Sync hronization approach enhanced with R etrieval and R e-ranking. Specifically, R $$^2$$ ComSync carries corresponding two novelties: (1) Ensemble hybrid retrieval. It equally considers the similarity in both code-comment semantics and change patterns when retrieval, thereby creating ICL prompts with effective examples. (2) Multi-turn re-ranking strategy. We derived three significant rules through large-scale CCS sample analysis. Given the inference results of LLMs, it progressively exploits three re-ranking rules to prioritize relatively correct-prone candidates. We evaluate R $$^2$$ ComSync using five recent LLMs on three CCS datasets covering both Java and Python programming languages, and make comparisons with five SOTA approaches. Extensive experiments demonstrate the superior performance of R $$^{2}$$ ComSync against other approaches. Moreover, both quantitative and qualitative analyses provide compelling evidence that the comments synchronized by our proposal exhibit significantly higher quality.- 25 February 2026
- Published by Springer Nature in Empirical Software Engineering
- Vol. 31 (4) , 84
Open AccessR$^2$ComSync: improving code-comment synchronization with in-context learning and rerankingCode-Comment Synchronization (CCS) aims to synchronize the comments with code changes in an automated fashion, thereby significantly reducing the workload of developers during software maintenance and evolution. While previous studies have proposed various solutions that have shown success, they often exhibit limitations, such as a lack of generalization ability or the need for extensive task-specific learning resources. This motivates us to investigate the potential of Large Language Models (LLMs) in this area. However, a pilot analysis proves that LLMs fall short of State-Of-The-Art (SOTA) CCS approaches because (1) they lack instructive demonstrations for In-Context Learning (ICL) and (2) many correct-prone candidates are not prioritized. To tackle the above challenges, we propose R $$^2$$ ComSync , an ICL-based code- Com ment Sync hronization approach enhanced with R etrieval and R e-ranking. Specifically, R $$^2$$ ComSync carries corresponding two novelties: (1) Ensemble hybrid retrieval. It equally considers the similarity in both code-comment semantics and change patterns when retrieval, thereby creating ICL prompts with effective examples. (2) Multi-turn re-ranking strategy. We derived three significant rules through large-scale CCS sample analysis. Given the inference results of LLMs, it progressively exploits three re-ranking rules to prioritize relatively correct-prone candidates. We evaluate R $$^2$$ ComSync using five recent LLMs on three CCS datasets covering both Java and Python programming languages, and make comparisons with five SOTA approaches. Extensive experiments demonstrate the superior performance of R $$^{2}$$ ComSync against other approaches. Moreover, both quantitative and qualitative analyses provide compelling evidence that the comments synchronized by our proposal exhibit significantly higher quality. - Open Access
Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations
Pre-trained or fine-tuned on large code corpora, Large Language Models (LLMs) have demonstrated strong performance in code completion tasks. However, their embedded knowledge is constrained by the timeliness of training data, which often includes code using deprecated APIs. Consequently, LLMs frequently generate deprecated APIs that will no longer be supported in future versions of third-party libraries. While retraining LLMs on updated codebases could refresh their API knowledge, this approach is computationally expensive. Recently, lightweight model editing methods have emerged to efficiently correct specific knowledge in LLMs. However, it remains unclear whether these methods can effectively update deprecated API knowledge and enable edited models to generate up-to-date APIs. To address this gap, we conduct the first systematic study applying 10 state-of-the-art model editing techniques to update deprecated API knowledge in three LLMs: Qwen2.5-Coder, StarCoder2, and DeepSeek-Coder. We introduce EDAPIBench, a dedicated benchmark featuring over 70 deprecated APIs from 8 popular Python libraries, with more than 3,000 editing instances. Our results show that the parameter-efficient fine-tuning method AdaLoRA achieves the best performance in enabling edited models to generate correct, up-to-date APIs, but falls short in Specificity (i.e., the editing influences untargeted knowledge). To resolve this, we propose AdaLoRA-L, which defines "Common API Layers" (layers within the LLMs with high importance across all APIs, storing general knowledge and excluded from editing) and restricts edits exclusively to "Specific API Layers" (layers with high importance only for the target API, storing the API-specific knowledge). Experimental results demonstrate that AdaLoRA-L significantly improves Specificity while maintaining comparable performance across other evaluation metrics.
Open AccessLightweight Model Editing for LLMs to Correct Deprecated API Recommendations
Pre-trained or fine-tuned on large code corpora, Large Language Models (LLMs) have demonstrated strong performance in code completion tasks. However, their embedded knowledge is constrained by the timeliness of training data, which often includes code using deprecated APIs. Consequently, LLMs frequently generate deprecated APIs that will no longer be supported in future versions of third-party libraries. While retraining LLMs on updated codebases could refresh their API knowledge, this approach is computationally expensive. Recently, lightweight model editing methods have emerged to efficiently correct specific knowledge in LLMs. However, it remains unclear whether these methods can effectively update deprecated API knowledge and enable edited models to generate up-to-date APIs. To address this gap, we conduct the first systematic study applying 10 state-of-the-art model editing techniques to update deprecated API knowledge in three LLMs: Qwen2.5-Coder, StarCoder2, and DeepSeek-Coder. We introduce EDAPIBench, a dedicated benchmark featuring over 70 deprecated APIs from 8 popular Python libraries, with more than 3,000 editing instances. Our results show that the parameter-efficient fine-tuning method AdaLoRA achieves the best performance in enabling edited models to generate correct, up-to-date APIs, but falls short in Specificity (i.e., the editing influences untargeted knowledge). To resolve this, we propose AdaLoRA-L, which defines "Common API Layers" (layers within the LLMs with high importance across all APIs, storing general knowledge and excluded from editing) and restricts edits exclusively to "Specific API Layers" (layers with high importance only for the target API, storing the API-specific knowledge). Experimental results demonstrate that AdaLoRA-L significantly improves Specificity while maintaining comparable performance across other evaluation metrics.
- Open Access
R2ComSync: Improving Code-Comment Synchronization with In-Context Learning and Reranking
Code-Comment Synchronization (CCS) aims to synchronize the comments with code changes in an automated fashion, thereby significantly reducing the workload of developers during software maintenance and evolution. While previous studies have proposed various solutions that have shown success, they often exhibit limitations, such as a lack of generalization ability or the need for extensive task-specific learning resources. This motivates us to investigate the potential of Large Language Models (LLMs) in this area. However, a pilot analysis proves that LLMs fall short of State-Of-The-Art (SOTA) CCS approaches because (1) they lack instructive demonstrations for In-Context Learning (ICL) and (2) many correct-prone candidates are not prioritized.To tackle the above challenges, we propose R2ComSync, an ICL-based code-Comment Synchronization approach enhanced with Retrieval and Re-ranking. Specifically, R2ComSync carries corresponding two novelties: (1) Ensemble hybrid retrieval. It equally considers the similarity in both code-comment semantics and change patterns when retrieval, thereby creating ICL prompts with effective examples. (2) Multi-turn re-ranking strategy. We derived three significant rules through large-scale CCS sample analysis. Given the inference results of LLMs, it progressively exploits three re-ranking rules to prioritize relatively correct-prone candidates. We evaluate R2ComSync using five recent LLMs on three CCS datasets covering both Java and Python programming languages, and make comparisons with five SOTA approaches. Extensive experiments demonstrate the superior performance of R2ComSync against other approaches. Moreover, both quantitative and qualitative analyses provide compelling evidence that the comments synchronized by our proposal exhibit significantly higher quality.}
Open AccessR2ComSync: Improving Code-Comment Synchronization with In-Context Learning and Reranking
Code-Comment Synchronization (CCS) aims to synchronize the comments with code changes in an automated fashion, thereby significantly reducing the workload of developers during software maintenance and evolution. While previous studies have proposed various solutions that have shown success, they often exhibit limitations, such as a lack of generalization ability or the need for extensive task-specific learning resources. This motivates us to investigate the potential of Large Language Models (LLMs) in this area. However, a pilot analysis proves that LLMs fall short of State-Of-The-Art (SOTA) CCS approaches because (1) they lack instructive demonstrations for In-Context Learning (ICL) and (2) many correct-prone candidates are not prioritized.To tackle the above challenges, we propose R2ComSync, an ICL-based code-Comment Synchronization approach enhanced with Retrieval and Re-ranking. Specifically, R2ComSync carries corresponding two novelties: (1) Ensemble hybrid retrieval. It equally considers the similarity in both code-comment semantics and change patterns when retrieval, thereby creating ICL prompts with effective examples. (2) Multi-turn re-ranking strategy. We derived three significant rules through large-scale CCS sample analysis. Given the inference results of LLMs, it progressively exploits three re-ranking rules to prioritize relatively correct-prone candidates. We evaluate R2ComSync using five recent LLMs on three CCS datasets covering both Java and Python programming languages, and make comparisons with five SOTA approaches. Extensive experiments demonstrate the superior performance of R2ComSync against other approaches. Moreover, both quantitative and qualitative analyses provide compelling evidence that the comments synchronized by our proposal exhibit significantly higher quality.}
- Open Access
Towards Understanding Bugs in Distributed Training and Inference Frameworks for Large Language Models
With the rapid development of large language models (LLMs), distributed training and inference frameworks like DeepSpeed have become essential for scaling model training and inference across multiple GPUs or nodes. However, the increasing complexity of these frameworks brings non-trivial software bugs, which may degrade training performance, cause unexpected failures, and result in significant resource waste. Understanding framework bugs' characteristics is fundamental for quality assurance, allowing the design of more effective debugging and repair methods. Thus, our paper conducts the first large-scale empirical analysis of 308 fixed bugs across three popular distributed training/inference frameworks: DeepSpeed, Megatron-LM, and Colossal-AI. We examine bug symptoms, root causes, bug identification and fixing efforts, and common low-effort fixing strategies. Additionally, the distributed nature of these frameworks introduces unique bug root causes, such as allocation strategy error and distributed communication error. Diagnosing and fixing complex bugs remains challenging due to factors like the disconnect between symptoms and root causes, high bug reproduction costs, and low-level or cross-component interactions. Interestingly, we observe that 48% of bug fixes require minimal code changes (<=10 LOC) and follow simple strategies such as conditional logic optimization, parameter handling enhancement, or version compatibility handling, indicating potential for automation. Based on these insights, we offer several implications for improving the reliability of both distributed training and inference frameworks and their dependent LLM projects, while also identifying opportunities to leverage LLM-based tools for automated debugging and repair.
Open AccessTowards Understanding Bugs in Distributed Training and Inference Frameworks for Large Language Models
With the rapid development of large language models (LLMs), distributed training and inference frameworks like DeepSpeed have become essential for scaling model training and inference across multiple GPUs or nodes. However, the increasing complexity of these frameworks brings non-trivial software bugs, which may degrade training performance, cause unexpected failures, and result in significant resource waste. Understanding framework bugs' characteristics is fundamental for quality assurance, allowing the design of more effective debugging and repair methods. Thus, our paper conducts the first large-scale empirical analysis of 308 fixed bugs across three popular distributed training/inference frameworks: DeepSpeed, Megatron-LM, and Colossal-AI. We examine bug symptoms, root causes, bug identification and fixing efforts, and common low-effort fixing strategies. Additionally, the distributed nature of these frameworks introduces unique bug root causes, such as allocation strategy error and distributed communication error. Diagnosing and fixing complex bugs remains challenging due to factors like the disconnect between symptoms and root causes, high bug reproduction costs, and low-level or cross-component interactions. Interestingly, we observe that 48% of bug fixes require minimal code changes (<=10 LOC) and follow simple strategies such as conditional logic optimization, parameter handling enhancement, or version compatibility handling, indicating potential for automation. Based on these insights, we offer several implications for improving the reliability of both distributed training and inference frameworks and their dependent LLM projects, while also identifying opportunities to leverage LLM-based tools for automated debugging and repair.