Xianchuan Wang

Dr. Xianchuan Wang


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
25 February 2025 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
BLBen Lu
Ben Lu
XWXianchuan Wang
Xianchuan Wang
WMWenkai Ming
Wenkai Ming
XWXianchao Wang
Xianchao Wang

26 September 2025 in Journal of Big Data
Verified
Journal Article
Open access
PDF file
BLBen Lu
Ben Lu
XWXianchuan Wang
Xianchuan Wang
WMWenkai Ming
Wenkai Ming
XWXianchao Wang
Xianchao Wang
With the advancement of text summarization technology, the issue of hallucinations in summaries has garnered increasing attention. Pretrained models often incorporate additional factual information to minimize the occurrence of hallucinations. In research on text summarization using LLMs, accurate samples are typically provided via a chain-of-thought approach, enabling the model to learn the implicit relationship between the source text and the target summary. To address the hallucination problem in text summarization, this paper proposes CLSeq and Nscp, which are specifically designed for pre-trained models and LLMs, respectively. CLSeq integrates the strengths of human-generated summaries and model-generated summaries to produce high-quality positive samples as target, while refining the loss function to handle negative samples more effectively. Nscp provides negative examples and explanatory information through the chain-of-thought mechanism. These strategies aim to enhance the model’s understanding of the characteristics and causes of hallucinations, thereby reducing the likelihood of factual inconsistencies in the summaries. Experimental results demonstrate that both methods effectively mitigate the hallucination problem in text summarization and exhibit a certain degree of robustness.

19 July 2024 in Research Square
Verified
Preprint
Open access
PDF file
BLBen Lu
Ben Lu
XWXianchuan Wang
Xianchuan Wang
WMWenkai Ming
Wenkai Ming
XWXianchao Wang
Xianchao Wang
Document-level entity relation extraction aims to extract all relations between entity pairs from unstructured text. Aiming at the problems of multi-mention entity, long-distance entity Relation and complex relation reasoning, this paper proposes a document relation extraction Model TSDRE (Three stage document Relation extraction Model) based on text coreference resolution and relation reasoning. Firstly, the CorefQA model was used to resolve the referential pronouns in the document. Secondly, the document was cut by sentence, and the PRGC model was used to extract the relationship at sentence level. Finally, the information of entity pairs that may have complex relationships, relationship reasoning information and evidence statements are taken as known information, encoded and used as the input of the model, and the BERT model is used to reason about complex relationships and determine the possible relationship categories of entity pairs. The experimental results show that the proposed model is at least 0.18,0.15,0.21 higher than other comparison models in the three indicators of validation set F1, test set F1, and lgnF1. TSDRE can extract the entity pair relationship information contained in the document more accurately and comprehensively.

9 June 2025 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
XWXianchuan Wang
Xianchuan Wang
BLBen Lu
Ben Lu
WMWenkai Ming
Wenkai Ming
XWXianchao Wang
Xianchao Wang

15 June 2026 in PeerJ Computer Science
Verified
Journal Article
Open access
PDF file
XWXianchuan Wang
Xianchuan Wang
WMWenkai Ming
Wenkai Ming
XMXue Ma
Xue Ma
BLBen Lu
Ben Lu
Recommender systems face the challenge of processing massive amounts of interaction data. The underutilization of relationship information in these data, as well as the presence of noise, reduces the accuracy of recommendations and the generalization ability of recommendation models. To address this, we propose KGDRec—a multi-graph knowledge-enhanced denoising recommendation algorithm. First, a relation-aware multi-graph fusion strategy integrates user-item interactions, user-user trust relationships, and item-item relationships to enhance semantic representations and alleviate data sparsity. However, while multi-graph fusion enriches relational information, it also introduces noise. To tackle this, we design a denoising self-enhancement module that combines edge perturbation, stability weighting, and contrastive learning to suppress unreliable signals and improve representation consistency. Experiments on the Ciao, Epinions, and Yelp datasets demonstrate that KGDRec outperforms baseline models in terms of Hit Ratio (HR) and Normalized Discounted Cumulative Gain (NDCG) metrics, and enhances accuracy and generalization capability.

30 March 2023
Verified
Book Chapter
Closed access
PDF file
ZFZhenyuan Fu
Zhenyuan Fu
XWXianchuan Wang
Xianchuan Wang
BQBaofeng Qi
Baofeng Qi
XCXiuming Chen
Xiuming Chen
XWXianchao Wang
Xianchao Wang