Rushi Wang Contact

Hi, I'm Rushi Wang

I am a first-year Ph.D. student in the Information Systems program at Indiana University’s Kelley School of Business, where I am mentored by Professor Ankit Shah. My research focuses on AI for safety.

Selected Publications Google Scholar

Selected Publications

Google Scholar →

Please visit my Google Scholar page for a complete list of publications.

Peer-reviewed Publications

AuditBench Financial Statement Analysis Diagram

AAAI-2024 AI for Finance

AuditBench: A Benchmark for Large Language Models in Financial Statement Auditing

Rushi Wang, Jiateng Liu, Weijie Zhao, Shenglan Li, and Denghui Zhang

Proceedings of the AAAI-2024 Workshop on AI for Financial Services.

Paper

EMNLP-2025 AI Safety

Context Engineering for Trustworthiness: Rescorla–Wagner Steering Under Mixed and Inappropriate Contexts

Rushi Wang, Jiateng Liu, Cheng Qian, Yifan Shen, Yanzhou Pan, Zhaozhuo Xu, Ahmed Abbasi, Heng Ji, Denghui Zhang

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP-2025 Main Conference).

Paper

EMNLP-2026 Multimodal LLMs Temporal Reasoning

ChronoVision: Temporal Reasoning via Latent State Reconstruction

Yifan Shen, Jian Xu, Boyi Li, Yuner Zhang, Tianjiao Yu, Bingxuan Li, Houze Yang, Rushi Wang, Xu Cao

Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP-2026).

Paper

Context Conditioning in Large Language Models Diagram

IEEE IS-2026 AI Safety Context Engineering

Pavlov’s Dog and Large Language Models: The Double-Edged Power of Context Conditioning

Denghui Zhang, Rushi Wang, Jiateng Liu, Kezia Oketch, Yiyu Shi, Heng Ji, Ahmed Abbasi

IEEE Intelligent Systems, vol. 41, no. 2, pp. 56–62, 2026.

Paper

Interface Usability Heuristics for Computer-Use Agents Diagram

arXiv-2026 Human-Computer Interaction Computer-Use Agents

Augmenting Interface Usability Heuristics for Reliable Computer-Use Agents

Jiateng Liu, Rushi Wang, Bingxuan Li, Kunlun Zhu, Yifan Shen, Qingyun Wang, Ahmed Abbasi, Denghui Zhang, Heng Ji

arXiv preprint arXiv:2605.02729

Paper

Contact

Email: wangrus@iu.edu · r15990588570@gmail.com