Jiawei Tang

Dr. Jiawei Tang


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 April 2025 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
YLYanyi Liu
Yanyi Liu
QYQingwen Yang
Qingwen Yang
JTJiawei Tang
Jiawei Tang
TGTiezheng Guo
Tiezheng Guo
CWChen Wang
Chen Wang
YWYingyou Wen
Yingyou Wen
With the widespread application of large language models (LLMs) in natural language processing (NLP), hallucinations have become a significant impediment to their effective use of LLMs in industry applications. To address this challenge, we integrate existing hallucination detection and mitigation methods into a unified hallucination detection and mitigation framework. The framework consists of four main components: output parser, reference parser, fact verifier, and mitigator. These components collectively consolidate various hallucination detection and mitigation methods. Within this unified framework, we introduce the hierarchical semantic piece (HSP) for hallucination detection and mitigation. The HSP method extracts multi-granularity semantic pieces from both the reference material and the generated text. Sentence-level semantic pieces encapsulate global semantic information, while entity-level semantic pieces handle local semantic information. This method verifies the consistency between the generated text and the reference text at corresponding granularities, thereby enhancing the effectiveness of hallucination detection and mitigation. Experimental results show that the HSP method is very effective in detecting and mitigating hallucinations and shows lower computational resource consumption. Our method has great potential and promises for industry applications that rely on professionalism and reliability.

6 August 2024 in arXiv
Verified
Preprint
Open access
PDF file
TGTiezheng Guo
Tiezheng Guo
CWChen Wang
Chen Wang
YLYanyi Liu
Yanyi Liu
JTJiawei Tang
Jiawei Tang
PLPan Li
Pan Li
YWYingyou Wen
Yingyou Wen
Retrieving external knowledge and prompting large language models with relevant information is an effective paradigm to enhance the performance of question-answering tasks. Previous research typically handles paragraphs from external documents in isolation, resulting in a lack of context and ambiguous references, particularly in multi-document and complex tasks. To overcome these challenges, we propose a new retrieval framework IIER, that leverages Inter-chunk Interactions to Enhance Retrieval. This framework captures the internal connections between document chunks by considering three types of interactions: structural, keyword, and semantic. We then construct a unified Chunk-Interaction Graph to represent all external documents comprehensively. Additionally, we design a graph-based evidence chain retriever that utilizes previous paths and chunk interactions to guide the retrieval process. It identifies multiple seed nodes based on the target question and iteratively searches for relevant chunks to gather supporting evidence. This retrieval process refines the context and reasoning chain, aiding the large language model in reasoning and answer generation. Extensive experiments demonstrate that IIER outperforms strong baselines across four datasets, highlighting its effectiveness in improving retrieval and reasoning capabilities.

9 April 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SXSai Xu
Sai Xu
JLJun Liu
Jun Liu
JTJiawei Tang
Jiawei Tang
XLXiangjun Liu
Xiangjun Liu
LZLi Zhi
Li Zhi
This paper proposes a cloud-edge collaborative method for operational situation assessment to ensure the efficient and reliable operation of space-based information networks. By analyzing time-varying network topology characteristics, we establish a 14-dimensional assessment factor system that can characterize the operational situation of space-based information networks. Considering the resource constraints of satellites, traditional on-orbit assessment methods often lead to high latency and excessive resource consumption. A cloud-edge collaborative situation assessment method is introduced to enhance assessment efficiency. The proposed method first applies principal component analysis for dimensionality reduction, followed by pre-labeling situational factor data using an improved K-means clustering algorithm. The on-orbit assessment of individual satellites is then performed using a particle swarm optimization-support vector machine algorithm. Finally, a fusion assessment of the space-based information networks is conducted at the ground cloud center, incorporating situation weighting factors. Experimental results demonstrate that the proposed cloud-edge collaborative method improves assessment accuracy by 13% compared to baseline methods, significantly reduces average completion time, and maintains stable performance in large-scale satellite constellations.