Gengyu Wang's Homepage

Gengyu Wang (王庚聿)

I am a Founding Engineer and Researcher of the LLM Team at Genies. Previously, I worked for Watson Assistant at IBM. I was an MS student in Computer Science at Columbia University, directly advised by Prof. Kathleen McKeown on Natural Language Processing. I received my Bachelor’s degree in Computer Science from Yonsei University, South Korea in 2018. During my undergraduate study, I was advised by Prof. Seung-won Hwang at Data Intelligence Lab.

Contact: gengyu.wang at columbia.edu

Linkedin->

Twitter->

Google Scholar->

Experience

Genies, San Mateo, CA, USA
(Jan 2024 ~)
NLP Research Engineer, Founding the NLP Team at Genies, Working on LLM-powered AI Avatar and data insight discovery.

IBM Watson, New York, NY, USA
(2021 ~ 2024)
NLP Engineer and Research at Watson Assistant (intelligent virtual agent)

JD AI Research, JD.COM, Mountain View, California, USA
(2020)
NLP Research Intern (Mentor by Senior Director Dr. Jing Huang)

Education

M.S. in Computer Science, Columbia University, New York City, USA (2019 ~ 2021)
Thesis: Fact-Checking Misinformation in Climate Change and COVID-19

B.S. in Computer Science, Yonsei University, Seoul, South Korea (2014 ~ 2018)

Research Interests

Chatbot, Dialog System, Question Answering, Fact-Checking

Publications

Check-COVID: Fact-Checking COVID-19 News Claims with Scientific Evidence
Gengyu Wang, Kate Harwood, Lawrence Chillrud, Amith Ananthram, Melanie Subbiah, Kathleen McKeown
ACL Findings- 2023 Annual Conference of the Association for Computational Linguistics. Toronto, Canada 2023

IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models
Haoxuan You, Rui Sun, Zhecan Wang, Long Chen, Gengyu Wang, Hammad A Ayyubi, Kai-Wei Chang, Shih-Fu Chang
EMNLP Findings- The 2023 Conference on Empirical Methods in Natural Language Processing. Singapore 2023

Benchmarking Language-agnostic Intent Classification for Virtual Assistant Platforms
Gengyu Wang*, Cheng Qian*, Lin Pan, Haode Qi, Ladislav Kunc, Saloni Potdar (*equal contribution)
NAACL – MIA Workshop on 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics. Seatle, WA 2022

Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants
Cheng Qian, Haode Qi, Gengyu Wang, Ladislav Kunc, Saloni Potdar
EMNLP – Industry Track on The 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, UAE 2022

Semantic Categorization of Social Knowledge for Commonsense Question Answering
Gengyu Wang, Xiaochen Hou, Diyi Yang, Kathleen McKeown, Jing Huang
EMNLP – SubstaiNLP2021 Workshop on The 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Evidence based Automatic Fact-Checking for Climate Change Misinformation
Gengyu Wang, Lawrence Chillrud, Kathleen McKeown
ICWSM – SocialSens Workshop on The International AAAI Conference on Web and Social Media, 2021

Soft Representation Learning for Sparse Transfer Learning
Haeju Park, Jinyoung Yeo, Gengyu Wang, Seung-won Hwang
ACL – Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 2019

Machine-Translated Knowledge Transfer for Commonsense Causal Reasoning
Jinyoung Yeo, Gengyu Wang, Hyunsouk Cho, Seungtaek Choi, Seung-won Hwang
AAAI – AAAI Conference on Artificial Intelligence, New Orleans, USA, 2018

Visual Choice of Plausible Alternatives: An Evaluation of Image-based Commonsense Causal Reasoning
Jinyoung Yeo, { Gengyu Wang, Gyungbok Lee}*, Seungtaek Choi, Hyunsouk Cho, Reinald Kim Amplayo, Seung-won Hwang
(* authors in alphabetical order with equal contribution)
LREC – Language Resources and Evaluation Conference, Miyazaki, Japan, 2018
Data Set

Services
Reviewer for ACL ARR 2024 Jun, ICML2024, ICLR2024, NeurIPS2023, EMNLP2023, NLPCC2023, LREC2020

Interests
Entrepreneurship
The Economist, Art

Language
Native Chinese, Fluent English and Korean