Xiaojun Wan

9.7k total citations · 1 hit paper
221 papers, 5.5k citations indexed

About

Xiaojun Wan is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Information Systems. According to data from OpenAlex, Xiaojun Wan has authored 221 papers receiving a total of 5.5k indexed citations (citations by other indexed papers that have themselves been cited), including 198 papers in Artificial Intelligence, 45 papers in Computer Vision and Pattern Recognition and 34 papers in Information Systems. Recurrent topics in Xiaojun Wan's work include Topic Modeling (161 papers), Natural Language Processing Techniques (134 papers) and Advanced Text Analysis Techniques (75 papers). Xiaojun Wan is often cited by papers focused on Topic Modeling (161 papers), Natural Language Processing Techniques (134 papers) and Advanced Text Analysis Techniques (75 papers). Xiaojun Wan collaborates with scholars based in China, Czechia and United States. Xiaojun Wan's co-authors include Jianguo Xiao, Jianwu Yang, Tianming Wang, Jiwei Tan, Yitao Cai, Xinjie Zhou, Ke Wang, Huiyu Cai, Jin-Ge Yao and Jianwu Yang and has published in prestigious journals such as Construction and Building Materials, Information Sciences and IEEE Transactions on Knowledge and Data Engineering.

In The Last Decade

Xiaojun Wan

205 papers receiving 5.1k citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

LLM-based NLG Evaluation: Current Status and Challenges

2025 15 citations Xiaojun Wan et al. profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Xiaojun Wan China	38	4.9k	926	727	231	185	221	5.5k
Ting Liu China	31	4.8k 1.0×	1.6k 1.7×	429 0.6×	418 1.8×	194 1.0×	127	5.8k
Dipanjan Das United States	26	4.0k 0.8×	654 0.7×	726 1.0×	247 1.1×	146 0.8×	68	4.8k
David Yarowsky United States	37	6.6k 1.4×	869 0.9×	645 0.9×	252 1.1×	305 1.6×	114	7.4k
Alan Ritter United States	28	4.4k 0.9×	880 1.0×	617 0.8×	189 0.8×	211 1.1×	71	5.2k
Benjamin Van Durme United States	33	3.7k 0.8×	569 0.6×	620 0.9×	205 0.9×	129 0.7×	186	4.1k
Ido Dagan Israel	45	7.1k 1.5×	980 1.1×	688 0.9×	153 0.7×	197 1.1×	218	7.7k
Ion Androutsopoulos Greece	32	5.3k 1.1×	1.6k 1.7×	375 0.5×	253 1.1×	159 0.9×	100	6.0k
Lidong Bing China	31	4.5k 0.9×	767 0.8×	541 0.7×	90 0.4×	208 1.1×	154	5.1k
Wen-tau Yih United States	42	6.8k 1.4×	1.4k 1.5×	1.2k 1.6×	281 1.2×	411 2.2×	91	7.6k
Jean Y. Wu United States	5	3.4k 0.7×	431 0.5×	477 0.7×	126 0.5×	127 0.7×	6	3.8k

Countries citing papers authored by Xiaojun Wan

Since Specialization

Citations

This map shows the geographic impact of Xiaojun Wan's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Xiaojun Wan with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Xiaojun Wan more than expected).

Fields of papers citing papers by Xiaojun Wan

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Xiaojun Wan. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Xiaojun Wan. The network helps show where Xiaojun Wan may publish in the future.

Co-authorship network of co-authors of Xiaojun Wan

This figure shows the co-authorship network connecting the top 25 collaborators of Xiaojun Wan. A scholar is included among the top collaborators of Xiaojun Wan based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Xiaojun Wan. Xiaojun Wan is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

1.

Pan, Liangming, et al.. (2025). Gödel Agent: A Self-Referential Agent Framework for Recursively Self-Improvement. 27890–27913.

2.

Gao, Mingqi, et al.. (2025). Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference. 4605–4629. 1 indexed citations

3.

Li, Lin, et al.. (2024). Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability. 15924–15951. 2 indexed citations

4.

Lu, Shuai, et al.. (2024). Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency. 1429–1450. 2 indexed citations

5.

Wan, Xiaojun, et al.. (2024). Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation. 2270–2286.

6.

Yang, Liming, et al.. (2024). History Matters: Temporal Knowledge Editing in Large Language Model. Proceedings of the AAAI Conference on Artificial Intelligence. 38(17). 19413–19421. 1 indexed citations

7.

Zhang, Junzhe & Xiaojun Wan. (2023). Exploring the Impact of Vision Features in News Image Captioning. 12923–12936. 2 indexed citations

8.

Yuan, Long, Jingping Qiu, Zhenbang Guo, et al.. (2023). Microscale and macroscale strength behaviors of blast furnace slag- cement based materials: Modeling and analysis. Construction and Building Materials. 376. 131016–131016. 17 indexed citations

9.

Sun, Renliang, et al.. (2021). Document-Level Text Simplification: Dataset, Criteria and Baseline. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 7997–8013. 23 indexed citations

10.

Dong, Qingxiu, Xiaojun Wan, & Yue Cao. (2021). ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation. 424–434. 15 indexed citations

11.

Cao, Yue, Haoran Wei, Boxing Chen, & Xiaojun Wan. (2021). Continual Learning for Neural Machine Translation. 3964–3974. 12 indexed citations

12.

Wang, Tianming, et al.. (2020). Heterogeneous Graph Transformer for Graph-to-Sequence Learning. 7145–7154. 33 indexed citations

13.

Wan, Xiaojun, et al.. (2020). Multimodal Transformer for Multimodal Machine Translation. 4346–4350. 82 indexed citations

14.

Yu, Zhiwei, et al.. (2020). Homophonic Pun Generation with Lexically Constrained Rewriting. 2870–2876. 13 indexed citations

15.

Yu, Zhiwei, Jiwei Tan, & Xiaojun Wan. (2018). A Neural Approach to Pun Generation. 37 indexed citations

16.

Tan, Jiwei, Xiaojun Wan, & Jianguo Xiao. (2017). Abstractive Document Summarization with a Graph-Based Attentional Neural Model. 1171–1181. 193 indexed citations

17.

Zhou, Xinjie, Xiaojun Wan, & Jianguo Xiao. (2016). Attention-based LSTM Network for Cross-Lingual Sentiment Classification. 247–256. 195 indexed citations

18.

Wan, Xiaojun, et al.. (2013). PPSGen: learning to generate presentation slides for academic papers. International Joint Conference on Artificial Intelligence. 2099–2105. 17 indexed citations

19.

Wan, Xiaojun. (2010). Towards a Unified Approach to Simultaneous Single-Document and Multi-Document Summarizations. 3(5882). 1137–1145. 60 indexed citations

20.

Wan, Xiaojun, Huiying Li, & Jianguo Xiao. (2010). Cross-Language Document Summarization Based on Machine Translation Quality Prediction. Meeting of the Association for Computational Linguistics. 917–926. 62 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact