Preprint

• ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition
  Yujie Liu*, Zonglin Yang*, Tong Xie, Jinjie Ni, Ben Gao, Yuqiang Li, Shixiang Tang, Wanli Ouyang, Erik Cambria, Dongzhan Zhou
  [pdf]

• LLM4SR: A Survey on Large Language Models for Scientific Research
  Ziming Luo*, Zonglin Yang*, Zexin Xu, Wei Yang, Xinya Du
  [pdf] [github paper collection]

• Logical Reasoning over Natural Language as Knowledge Representation: A Survey
  Zonglin Yang, Xinya Du, Rui Mao, Jinjie Ni, Erik Cambria
  [pdf] [LRNL-bench] (to come) [ACL 2023 NLRSE workshop poster] (not archival)

Publications

2025

• MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses
  Zonglin Yang, Wanhao Liu, Ben Gao, Tong Xie, Yuqiang Li, Wanli Ouyang, Soujanya Poria, Erik Cambria, Dongzhan Zhou
  in Proc. of ICLR 2025
  [pdf] [code and benchmark]

• Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
  Di Zhang, Jingdi Lei, Junxian Li, Xunzhi Wang, Yujie Liu, Zonglin Yang, Jiatong Li, Weida Wang, Suorong Yang, Jianbo Wu, Peng Ye, Wanli Ouyang, Dongzhan Zhou
  in Proc. of CVPR 2025
  [pdf]

2024

• Large Language Models for Automated Open-domain Scientific Hypotheses Discovery
  Zonglin Yang, Xinya Du, Junxian Li, Jie Zheng, Soujanya Poria, Erik Cambria
  in Proc. of ACL 2024 (Findings)
  Best Poster Award in [AI4Science Workshop]
  [pdf] [dataset and code]

• Language Models as Inductive Reasoners
  Zonglin Yang, Li Dong, Xinya Du, Hao Cheng, Erik Cambria, Xiaodong Liu, Jianfeng Gao, Furu Wei
  in Proc. of EACL 2024
  [pdf (preprint in 2022)] [dataset and code] [poster] [slides]

2023

• Task-Aware Self-Supervised Framework for Dialogue Discourse Parsing
  Wei Li, Luyao Zhu, Wei Shao, Zonglin Yang, Erik Cambria
  in Proc. of EMNLP 2023 (Findings)
  [pdf] [code]

• A Survey on Semantic Processing Techniques
  Zonglin Yang*, Rui Mao*, Kai He*, Xulang Zhang*, Guanyi Chen*, Jinjie Ni*, Erik Cambria
  in Information Fusion
  [pdf]

• Finding the Pillars of Strength for Multi-Head Attention
  Jinjie Ni, Rui Mao, Zonglin Yang, Han Lei, Erik Cambria
  in Proc. of ACL 2023
  [pdf] [code]

• End-to-end Case-Based Reasoning for Commonsense Knowledge Base Completion
  Zonglin Yang, Xinya Du, Erik Cambria, Claire Cardie
  in Proc. of EACL 2023 (oral)
  [pdf] [code] [EACL 2023 slides] [ICCBR 2023 TMG/BEAR workshop slides] (not archival)

2020

• Improving Event Duration Prediction via Time-aware Pre-training
  Zonglin Yang, Xinya Du, Alexander Rush, Claire Cardie
  in Proc. of EMNLP 2020 (Findings)
  [pdf] [collected data]