Heng Wang (王珩)
Hi there, thanks for visiting my website! I am a senior undergraduate student at Xi'an Jiaotong University, majoring in Computer Science.
I am interested in natural language reasoning and how to use language to interact with the physical world and humans, advised by Prof. Minnan Luo.
I have interned at UW NLP with Ph.D. student Shangbin Feng and Prof. Yulia Tsvetkov.
I am now working with Ph.D. student Ruiqi Zhong and Prof. Jacob Steinhardt at UC Berkeley.
My previous research includes natural language reasoning, spoiler detection, and AI agent safety. I co-lead LUD lab, an undergraduate research group @ XJTU.
I'm looking for Ph.D. positions starting in 25Fall!
Email  / 
Google Scholar  / 
Twitter  / 
Github
|
|
Research Interest
1) Language models for structures and networks, 2) Safety risks of super models, and 3) Building agents that interact with the world
|
Publications (* indicates equal contribution)
|
|
Can Language Models Solve Graph Problems in Natural Language?
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.
|
|
Detecting Spoilers in Movie Reviews with External Movie Knowledge and User Networks
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.
|
|
AdaptiveBackdoor: Backdoored Language Model Agents that Detect Human Overseers
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.
|
|
Can LLM Graph Reasoning Generalize beyond Pattern Memorization?
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.
|
|
Explaining Datasets in Words: Statistical Models with Natural Language Parameters
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.
|
|
Resolving Knowledge Conflicts in Large Language Models
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.
|
|
BotMoE: Twitter Bot Detection with Community-Aware Mixtures of Modal-Specific Experts
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.
|
|
TwiBot-22: Towards Graph-Based Twitter Bot Detection
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
|
Honors & Awards
- SenseTime Scholarship, 2023 (awarded to 30 students in China)
- National Scholarship, 2022 (0.2% nationwide)
- NeurIPS Scholar Award, 2023
- Golden Award (team 3rd place), ACM ICPC Shaanxi Provincial Programming Contest, 2023
- Silver Award (ranking 26/115), ACM ICPC Asia Hong Kong Regional, 2023
- Academic Research Award, Xi'an Jiaotong University, 2022
- Silver Award, CCF Collegiate Computer System and Programming Contest, 2022
- Dean's List, Xi'an Jiaotong University, 2022
|
Service
- Reviewer: ICLR (2025), NeurIPS (2024), COLM (2024), TIST(2024), EMNLP (2023), TOIS (2023), NeurIPS dataset and benchmark track (2022, 2023, 2024), NextGenAISafety@ICML (2024), AGI@ICLR (2024), SeT LLM@ICLR (2024)
- Volunteer: EMNLP (2023) (virtual)
|
Miscellaneous
- I enjoy playing the piano 🎹 and go.
- I am a big fan of Animenz.
|
|