Thrilled to announce that we has had three papers accepted at EMNLP 2025! Huge congratulations to all the authors for their incredible work. We are excited to share our latest research with the community.
Here’s a look at our accepted papers:
-
From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery
- Authors: Tianshi Zheng, Zheye Deng, Hong Ting Tsang, Weiqi Wang, Jiaxin Bai, Zihao Wang, Yangqiu Song
- This paper will be presented at the EMNLP 2025 Main Conference. It systematically reviews the evolution of Large Language Models in scientific discovery, proposing a three-level taxonomy to map their growing autonomy from tools to collaborators in the research lifecycle.
-
LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning
- Authors: Tianshi Zheng, Cheng Jiayang, Chunyang Li, Haochen Shi, Zihao Wang, Jiaxin Bai, Yangqiu Song, Ginny Wong, Simon See
- Also accepted to the EMNLP 2025 Main Conference, this work investigates the different logical inference mechanisms in LLMs. It provides insights into when different reasoning approaches are most effective and demonstrates how advanced strategies can significantly scale LLM reasoning capabilities.
-
On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions
- Authors: Weiqi Wang, Tianqing Fang, Haochen Shi, Baixuan Xu, Wenxuan Ding, Liyu Zhang, Wei Fan, Jiaxin Bai, Haoran Li, Xin Liu, Yangqiu Song
- Accepted to EMNLP 2025 Findings, this comprehensive survey examines over 150 papers to create a unified taxonomy for conceptualization in reasoning, focusing on the entity and event levels. The paper clarifies the process of abstracting instances into higher-level concepts to improve the generalizable reasoning of models.
We are incredibly proud of the hard work and dedication that went into this research. We look forward to presenting our findings and engaging with fellow researchers at EMNLP 2025