Publications

2025

Learning Structured Reasoning in Vision-Language Models via System 2 Inductive Bias
Haoqiang Kang, Enna Sachdeva, Piyush Gupta, Sangjae Bae, and Kwonjoon Lee
Conference on Computer Vision and Pattern Recognition, 2025.
[paper]

Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples
Fangxu Yu, Haoqiang Kang, Lai Jian, Shibo Hao, and Lianhui Qin
Under Review at ICML, 2025. Substantial Lead Contribution.
[paper]

2024

The FinBen: An Holistic Financial Benchmark for Large Language Models
NeurIPS Datasets and Benchmarks Tracks, 2024
[paper]

Comparing Hallucination Detection Metrics for Multilingual Generation
Haoqiang Kang, Terra Blevins, and Luke Zettlemoyer
[paper]

2023

EVER: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification
Haoqiang Kang, Juntong Ni, and Huaxiu Yao
[paper]

Hallucination of Large Language Models in Finance: An Empirical Examination
Haoqiang Kang and Xiao-Yang Liu
NeurIPS Workshop on I Can’t Believe It’s Not Better (ICBINB), 2023.
[paper]

Translate to Disambiguate: Zero-shot Multilingual Word Sense Disambiguation with Pretrained Language Models
Haoqiang Kang*, Terra Blevins*, and Luke Zettlemoyer
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2024. (Oral)
[paper]

More interesting papers are on the way:)