About me
I am a Third-year Master student at the Joint Graduate School (Double degree) of Southeast University and Monash University, advised by Prof. Guilin Qi. I received my Bachelor’s degree from Hefei University in June 2022. Also, I worked as a research intern under the guidance of Prof. Chenyu You at Stony Brook University in 2024.
My research areas include Natural Language Processing (NLP), Retrieval-Augmented Generation (RAG) and Knowledge Graphs (KG). Currently, my main research focus is on enhancing the performance of LLMs using heterogeneous data (text, graphs and tables). Additionally, I am also highly interested in multimodal (vision-language) models.
🎉 News
02-2025: Served as a reviewer for ACL ARR February 2025.
01-2025: One paper (UniHGKR) was accepted by NAACL (Main) 2025, Oral Paper, with a highest meta-review score of 5!
12-2024: One paper was accepted by AAAI 2025!
🎓 Education
Southeast University , 09/2022 - 2025.06 (expected)
- Mphil. in Artificial Intelligence. Advisor: Guilin Qi
Monash University , 09/2022 - 2025.06 (expected)
- M.S. in Artificial Intelligence.
Hefei University , 09/2017 - 06/2022
- B.S. in Electronic and Information Engineering
📝 Publications and Preprints
(* Refers to the authors having the equal contribution, and should be considered as co-first authors.)
Dehai Min, Zhiyang Xu, Guilin Qi, Lifu Huang, and Chenyu You. UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers (NAACL 2025, Oral), Code
Dehai Min*, Nan Hu*, Rihui Jin, Nuo Lin, Jiaoyan Chen, Yongrui Chen, Yu Li et al. Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data (NAACL 2024, Industry Track paper, Oral), Slides.
Yiming Tan*, Dehai Min*, Yu Li, Wenbo Li, Nan Hu, Yongrui Chen, and Guilin Qi. Can ChatGPT replace traditional KBQA models? An in-depth analysis of the question answering performance of the GPT LLM family (ISWC 2023, Oral), Code ,Slides
Nan Hu, Yike Wu, Guilin Qi, Dehai Min, Jiaoyan Chen, Jeff Z. Pan, and Zafar Ali. An empirical study of pre-trained language models in simple knowledge graph question answering (WWW Journal 2023) , Code
Jiaqi Li, Chuanyi Zhang, Miaozeng Du, Dehai Min, Yongrui Chen, and Guilin Qi. Three stream based multi-level event contrastive learning for text-video event extraction (EMNLP 2023, Oral) , Slides.
Yu Li, Shenyu Zhang, Rui Wu, Xiutian Huang, Yongrui Chen, Wenhao Xu, Guilin Qi, and Dehai Min. MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation (DASFAA 2024, Oral)
Rihui Jin, Yu Li, Guilin Qi, Nan Hu, Yuan-Fang Li, Jiaoyan Chen, Jianan Wang, Yongrui Chen, Dehai Min and Sheng Bi. HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding (AAAI 2025).
Work in progress
- Yiming Tan*, Dehai Min*, Huikang Hu, Nuo Lin, Guilin Qi, Sheng Bi et al. ELLMKGQA: Evaluation Framework of Large-language Model as Knowledge Graph on Question-Answering (submitted, under review).
🧑🏫 Internship
Stony Brook University , 07/2024 - 11/2024
- Research Intern , Advisor: Chenyu You
👨💻 Academic services
Reviewer of ACL ARR 2025
Reviewer of IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Subreviewer of the International Semantic Web Conference (ISWC 2024)
🏅 Competitions
( I was an active participant in programming competitions during my undergraduate years. )
- ACM-ICPC (International Collegiate Programming Contest) , Asian Regional Contest (Shanghai Site and others), 2019-2020, Silver Medal. individual / team
- CCPC-Finals (China Collegiate Programming Contest National Finals), 2019, 21st place, Silver Medal
- 16th Baidu Star Programming Contest, National Semi-Finals, 2019, 154th place (154/13900+)
- Anhui Province Collegiate Programming Contest, First Prize (2 times, 2019, 2020), Champion (1 time, 2020)
- Codeforces Rating: 2108 (Master), link
