Jiawei Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jiawei Lu has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Ai Han
JD.com, Beijing, China
1 shared publication - Fangming Liu
Huazhong University of Science and Technology, Wuhan, China
1 shared publication - Haoye Wang
Hangzhou City University, School of Computer and Computing Science, Hangzhou, China
1 shared publication - Jiaxing Wang
JD.com, Beijing, China
1 shared publication - Junhua Shu
JD.com, Beijing, China
1 shared publication - Ke Zhang
JD.com, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1371-1386
FlexMARL: Graph-Driven Rollout-Training Co-Design for LLM-Based Multi-Agent Reinforcement Learning
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1371-1386
Open AccessFlexMARL: Graph-Driven Rollout-Training Co-Design for LLM-Based Multi-Agent Reinforcement Learning
- Open Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 191-203
Instructive Code Retriever: Learn from Large Language Model's Feedback for Code Intelligence Tasks
Recent studies proposed to leverage large language models (LLMs) with In-Context Learning (ICL) to handle code intelligence tasks without fine-tuning. ICL employs task instructions and a set of examples as demonstrations to guide the model in generating accurate answers without updating its parameters. While ICL has proven effective for code intelligence tasks, its performance heavily relies on the selected examples. Previous work has achieved some success in using BM25 to retrieve examples for code intelligence tasks. However, existing approaches lack the ability to understand the semantic and structural information of queries, resulting in less helpful demonstrations. Moreover, they do not adapt well to the complex and dynamic nature of user queries in diverse domains. In this paper, we introduce a novel approach named Instructive Code Retriever (ICR), which is designed to retrieve examples that enhance model inference across various code intelligence tasks and datasets. We enable ICR to learn the semantic and structural information of the corpus by a tree-based loss function. To better understand the correlation between queries and examples, we incorporate the feedback from LLMs to guide the training of the retriever. Experimental results demonstrate that our retriever significantly outperforms state-of-the-art approaches. We evaluate our model's effectiveness on various tasks, i.e., code summarization, program synthesis, and bug fixing. Compared to previous state-of-the-art algorithms, our method achieved improvements of 50.0% and 90.0% in terms of BLEU-4 for two code summarization datasets, 74.6% CodeBLEU on program synthesis dataset, and increases of 3.6 and 3.2 BLEU-4 on two bug fixing datasets.
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 191-203
Open AccessInstructive Code Retriever: Learn from Large Language Model's Feedback for Code Intelligence Tasks
Recent studies proposed to leverage large language models (LLMs) with In-Context Learning (ICL) to handle code intelligence tasks without fine-tuning. ICL employs task instructions and a set of examples as demonstrations to guide the model in generating accurate answers without updating its parameters. While ICL has proven effective for code intelligence tasks, its performance heavily relies on the selected examples. Previous work has achieved some success in using BM25 to retrieve examples for code intelligence tasks. However, existing approaches lack the ability to understand the semantic and structural information of queries, resulting in less helpful demonstrations. Moreover, they do not adapt well to the complex and dynamic nature of user queries in diverse domains. In this paper, we introduce a novel approach named Instructive Code Retriever (ICR), which is designed to retrieve examples that enhance model inference across various code intelligence tasks and datasets. We enable ICR to learn the semantic and structural information of the corpus by a tree-based loss function. To better understand the correlation between queries and examples, we incorporate the feedback from LLMs to guide the training of the retriever. Experimental results demonstrate that our retriever significantly outperforms state-of-the-art approaches. We evaluate our model's effectiveness on various tasks, i.e., code summarization, program synthesis, and bug fixing. Compared to previous state-of-the-art algorithms, our method achieved improvements of 50.0% and 90.0% in terms of BLEU-4 for two code summarization datasets, 74.6% CodeBLEU on program synthesis dataset, and increases of 3.6 and 3.2 BLEU-4 on two bug fixing datasets.