Lin Ren (任林)#

Lin Ren is a Ph.D. student at the School of Computer Science and Engineering, Southeast University, China, advised by Prof. Guohui Xiao and Prof. Guilin Qi. Before joining Southeast University, Lin received a master’s degree in 2024 and a bachelor’s degree in 2021, both from the University of South China.

Lin’s primary research interest is Knowledge Representation and Reasoning (KRR), with contributions from knowledge graphs, natural language processing, and large language models. A particular emphasis is on Virtual Knowledge Graphs (VKGs), also known as Ontology-based Data Access (OBDA), where the aim is to reduce the manual effort of constructing mappings and to suppress silent failures in question answering. A second line of work evaluates and strengthens the symbolic reasoning ability of large language models, including systematic benchmarking on Answer Set Programming (ASP).

Earlier work, carried out during the bachelor’s and master’s studies, applied causal inference to natural language processing, covering causal relation extraction in financial text as well as debiasing for information extraction and knowledge graph completion. The code behind most of these works is released as open source on GitHub.

Contact#

CV　PDF
E-mail　renlin@seu.edu.cn
Google Scholar　Citations
GitHub　HomuraT
CSDN　Blog
Address　School of Computer Science and Engineering, Southeast University, Nanjing, China

Research Interests#

Knowledge Representation and Reasoning (KRR)
Virtual Knowledge Graphs, Ontology-based Data Access (OBDA)
Answer Set Programming (ASP)
Large Language Models
Causal Inference
Information Extraction

Education#

Sept 2024 - present, Ph.D. student in Software Engineering
Southeast University, Nanjing, China
School of Computer Science and Engineering
advisors Prof. Guohui Xiao and Prof. Guilin Qi

June 2024, Master of Electronic Information
University of South China, Hengyang, Hunan, China
School of Computer Science and Technology
advisors Prof. Yongbin Liu and Prof. Chunping Ouyang
thesis “Research on Debiasing Knowledge Graphs based on Causal Inference” (in Chinese)

June 2021, Bachelor of Engineering in Software Engineering
University of South China, Hengyang, Hunan, China
School of Computer Science and Technology
thesis “Causal Relation Extraction from Financial Text” (in Chinese)

Publications#

My name is in bold. Titles link to the paper where a public version is available; entries without a public link are shown as plain text.

2026#

EvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization
Dai, X., Xin, Z., Hu, H., Ren, L., Jin, R., Xiao, G., Qi, G., Dong, K., Du, Z., and Zhang, Y.
Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI-26)
Large Reasoning Models Preference Optimization

NaVQA: Mitigating Silent Failures in Question Answering over Virtual Knowledge Graph
Xiao, G., Xue, H., Ren, L., Geng, Y., Qi, G., Zhang, S., Guo, D., Di Panfilo, M., Lanti, D., and Ding, L.
Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI-26)
Virtual Knowledge Graph Question Answering

Information-Needs-Guided Virtual Knowledge Graph Enrichment via Large Language Models
Ren, L., Xiao, G., Qi, G., Du, W., Geng, Y., Xue, H., Yue, Z., Li, M., Di Panfilo, M., Lanti, D., Hamaz, K., and Ding, L.
Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI-26)
Virtual Knowledge Graph Large Language Models

Code as Representation: A Compilable Parsing Paradigm for Academic Documents
Jin, R., Wang, J., Liang, M., Gao, Y., Li, Y., Dong, K., Qi, G., Ren, L., Chen, Y., Dai, X., Li, J., Wu, T., and Haffari, G.
ACM International Conference on Multimedia (ACM MM 2026)
Document Parsing Multimodality

2025#

LLM4VKG: Leveraging Large Language Models for Virtual Knowledge Graph Construction
Xiao, G., Ren, L., Qi, G., Xue, H., Panfilo, M. D., and Lanti, D.
Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI-25)
Virtual Knowledge Graph Large Language Models · code

DyLas: A dynamic label alignment strategy for large-scale multi-label text classification
Ren, L., Liu, Y., Ouyang, C., Yu, Y., Zhou, S., He, Y., and Wan, Y.
Information Fusion, 120, 103081
Large-scale Multi-label Text Classification Large Language Model Causal Inference · code

Can LLMs Solve ASP Problems? Insights from a Benchmarking Study
Ren, L., Xiao, G., Qi, G., Geng, Y., and Xue, H.
International Conference on Principles of Knowledge Representation and Reasoning (KR 2025)
Answer Set Programming Large Language Models Benchmark · code

2024#

Multimodal emotion recognition based on hierarchical fusion strategy and contextual information embedding
Minglong, S., Chunping, O., Yongbin, L., and Lin, R.
Beijing Da Xue Xue Bao, 60(3), 393-402
Multimodality Emotion Recognition

2023#

CoVariance-based causal debiasing for entity and relation extraction
Ren, L., Liu, Y., Cao, Y., and Ouyang, C.
Findings of the Association for Computational Linguistics: EMNLP 2023, 2627-2640
Information Extraction Causal Inference · code

Causal inference-based debiasing framework for knowledge graph completion
Ren, L., Liu, Y., and Ouyang, C.
International Semantic Web Conference (ISWC 2023), 328-347. Cham: Springer Nature Switzerland
Knowledge Graph Completion Causal Inference · code

Counterfactual can be strong in medical question and answering
Yang, Z., Liu, Y., Ouyang, C., Ren, L., and Wen, W.
Information Processing & Management, 60(4), 103408
Medical Question Answering Causal Inference

Joint span and token framework for few-shot named entity recognition
Fang, W., Liu, Y., Ouyang, C., Ren, L., Li, J., and Wan, Y.
AI Open, 4, 111-119
Information Extraction Few-shot Learning