|
I am an incoming Ph.D. student at University of Illinois at Urbana-Champaign (UIUC). Currently, I am a senior undergraduate student majoring in computer science at Xi'an Jiaotong University and an intern at Moonshot AI. I am interested in interpretability, reasoning, and agents. I have interned at UW NLP with Ph.D. student Shangbin Feng and Prof. Yulia Tsvetkov. I am also fortunate to work with Ph.D. student Ruiqi Zhong and Prof. Jacob Steinhardt at UC Berkeley. My previous research includes natural language reasoning and AI agent safety. I co-lead LUD lab, an undergraduate research group @ XJTU. Email / Google Scholar / Twitter / Github |
|
|
1) Interpretability, 2) reasoning for structured data, and 3) Building agents for real-world tasks |
|
|
|
Heng Wang*, Shangbin Feng*, Tianxing He, Zhaoxuan Tan, Xiaochuang Han, Yulia Tsvetkov Proceedings of NeurIPS, 2023 (spotlight; 3.4% acceptance rate) code / poster Are language models graph reasoners? We propose the NLGraph benchmark, a test bed for graph-based reasoning designed for language models in natural language. We find that LLMs are preliminary graph thinkers while the most advanced graph reasoning tasks remain an open research question. |
|
Heng Wang, Wenqian Zhang, Yuyang Bai, Zhaoxuan Tan, Shangbin Feng, Qinghua Zheng, Minnan Luo Proceedings of EMNLP, 2023 code We curate a large-scale network-based spoiler detection dataset (LCS), a movie knowledge base (UKM), and propose MVSD, a Multi-View Spoiler Detection framework that takes into account external knowledge and user interaction networks. |
|
Heng Wang, Ruiqi Zhong, Jiaxin Wen, Jacob Steinhardt ICML 2024 @ NextGenAISafety We speculate a new form of cyber attack, where an LM agent is backdoored to detect whether its actions will be overseen by humans and act maliciously when effective oversight is not present, and provide concrete proof-of-concept with AutoGPT. |
|
Yizhuo Zhang*, Heng Wang*, Shangbin Feng*, Zhaoxuan Tan, Xiaochuang Han, Tianxing He, Yulia Tsvetkov , Tianxing He, Yulia Tsvetkov EMNLP 2024, findings code While instruction tuning produces promising graph LLMs, can they generalize beyond patterns in the training data? Mostly no, especially from synthetic to real-world problems, while we explore preliminary solutions. |
|
Ruiqi Zhong, Heng Wang, Dan Klein, Jacob Steinhardt Proceedings of NeurIPS, 2024 code We build a framework that can use natural language predicates to parameterize a wide range of statistical models, and show that it is versatile, useful, and applicable to both text and vision domains, and explains sophisticated concepts that classical methods struggle to produce. |
|
Yike Wang*, Shangbin Feng*, Heng Wang, Weijia Shi, Vidhisha Balachandran , Tianxing He, Yulia Tsvetkov Proceedings of COLM, 2024 code We introduce KNOWLEDGE CONFLICT, an evaluation framework for simulating contextual knowledge conflicts and quantitatively evaluating LLMs' abilities to handle knowledge conflicts. |
|
Yuhan Liu, Zhaoxuan Tan, Heng Wang, Shangbin Feng, Qinghua Zheng, Minnan Luo Proceedings of SIGIR 2023. code We propose community-aware mixture-of-experts to address two challenges in detecting advanced Twitter bots: manipulated features and diverse communities. |
|
Shangbin Feng*, Zhaoxuan Tan*, Herun Wan*, Ningnan Wang*, Zilong Chen*, Binchi Zhang*, Qinghua Zheng, Wenqian Zhang, Zhenyu Lei, Shujie Yang, Xinshun Feng, Qingyue Zhang, Hongrui Wang, Yuhan Liu, Yuyang Bai, Heng Wang, Zijian Cai, Yanbo Wang, Lijing Zheng, Zihan Ma, Jundong Li, Minnan Luo Proceedings of NeurIPS, Datasets and Benchmarks Track, 2022. website / GitHub / bibtex / poster We present TwiBot-22, the largest graph-based Twitter bot detection benchmark to date, which provides diversified entities and relations in Twittersphere and has considerably better annotation quality. |
|
|
 |
Xi'an Jiaotong University
2021.09 - 2025.07 (Expected) B.E. in Computer Science GPA: 93.66 / 100.0 (4.09 / 4.3) Advisor: Prof. Minnan Luo |
 |
University of California, Berkeley
2023.08 - 2023.12 BGA Student (Visiting Student) GPA: 4.00 / 4.00 |
|
|
 |
Luo lab Undergraduate Division (LUD) @ XJTU
Member 2021.08 - 2024.6 Director 2024.6 - present Conducted research on various topics including social network analysis, and graph neural networks pre-training. Advisor: Prof. Minnan Luo |
|
|
|
|
Template courtesy: Jon Barron. |