Kung-Hsiang (Steeve) Huang

Research Scientist
Salesforce AI Research

Palo Alto, California

khhuang3@illinois.edu

About Me

I'm a research scientist at Salesforce AI Research, driven by a mission to make AI more trustworthy and reduce the spread of false information. To achieve this goal, I've worked towards several key research directions: fact-checking (COLING 2022), fake news detection (NAACL 2022, ACL 2023), faithfulness enhancement and evaluation (EACL 2023 Findings, NAACL 2024, NAACL 2024), and factual error correction (ACL 2023, Arxiv 2023).

I earned my PhD at the University of Illinois Urbana-Champaign, under the guidance of my amazing advisor Prof. Heng Ji. During my PhD study, I've received the Amazon Science Ph.D. Fellowship. Before joining UIUC, I obtained my master's degree from the University of Southern California and my bachelor's degree from the Hong Kong University of Science and Technology.

Selected Publications
* Equal Contribution

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

2024

SafeWorld: Geo-Diverse Safety Alignment
Da Yin*, Haoyi Qiu*, Kung-Hsiang Huang, Kai-Wei Chang, Nanyun Peng
NeurIPS 2024
Bibtex

@inproceedings{da-etal-2024-safe,
    title = "SafeWorld: Geo-Diverse Safety Alignment",
    author = "Da Yin, Haoyi Qiu, Kung-Hsiang Huang, Kai-Wei Chang, Nanyun Peng",
    booktitle = "Thirty-eighth Conference on Neural Information Processing Systems",
    year="2024",
}

CRMArena: A Benchmark for Testing the Knowledge of Large Language Models in Customer Relationship Management
Kung-Hsiang Huang, Akshara Prabhakar, Sidharth Dhawan, Yixin Mao, Huan Wang, Silvio Savarese, Caiming Xiong, Philippe Laban, Chien-Sheng Wu
Arxiv
PDF Bibtex Code Dataset Leaderboard

@misc{huang-etal-2024-crmarena,
  title = "CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments",
  author = "Huang, Kung-Hsiang  and
    Prabhakar, Akshara  and
    Dhawan, Sidharth  and
    Mao, Yixin  and
    Wang, Huan  and
    Savarese, Silvio  and
    Xiong, Caiming  and
    Laban, Philippe  and
    Wu, Chien-Sheng",
  year = "2024",
  archivePrefix = "arXiv",
  eprint={2411.02305},
  primaryClass={cs.CL}
}

Evaluating Cultural and Social Awareness of LLM Web Agents
Haoyi Qiu, Alexander R. Fabbri, Divyansh Agarwal, Kung-Hsiang Huang, Sarah Tan, Nanyun Peng, Chien-Sheng Wu
Arxiv
PDF Bibtex

@misc{qiu2024evaluating,
      title={Evaluating Cultural and Social Awareness of LLM Web Agents}, 
      author={Qiu, Haoyi and Fabbri, Alexander R. and Agarwal, Divyansh and Huang, Kung-Hsiang and Tan, Sarah and Peng, Nanyun and Wu, Chien-Sheng},
      year={2024},
      eprint={2410.23252},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models
Kung-Hsiang Huang, Hou Pong Chan, Yi R Fung, Haoyi Qiu, Mingyang Zhou, Shafiq Joty, Shih-Fu Chang, Heng Ji.
Arxiv.
PDF Bibtex Reading List

@misc{huang-etal-2024-chart,
    title = "From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models",
    author = "Huang, Kung-Hsiang and Chan, Hou Pong and Fung, Yi R. and Qiu, Haoyi and Zhou, Mingyang and Joty, Shafiq and Chang, Shih-Fu and Ji, Heng",
    year={2024},
    eprint={2403.12027},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning.
Kung-Hsiang Huang, Mingyang Zhou, Hou Pong Chan, Yi R Fung, Zhenhailong Wang, Lingyu Zhang, Shih-Fu Chang, Heng Ji.
ACL 2024 Findings.
PDF Bibtex Project Code

@inproceedings{huang-etal-2023-do,
    title = "Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning",
    author = "Huang, Kung-Hsiang  and
      Zhou, Mingyang and
      Chan, Hou Pong  and
      Fung, Yi R. and
      Wang, Zhenhailong and
      Zhang, Lingyu and
      Chang, Shih-Fu and
      Ji, Heng",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year="2024",
    publisher = "Association for Computational Linguistics",
}

Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles.
Kung-Hsiang Huang, Philippe Laban, Alexander R. Fabbri, Prafulla Kumar Choubey, Shafiq Joty, Caiming Xiong, Chien-Sheng Wu.
NAACL 2024.
PDF Bibtex Dataset

@inproceedings{huang-etal-2024-embrace,
    title = "Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles.",
    author = "Kung-Hsiang Huang and Philippe Laban and Alexander R. Fabbri and Prafulla Kumar Choubey and Shafiq Joty and Caiming Xiong and Chien-Sheng Wu",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    year = "2024",
    publisher = "Association for Computational Linguistics",
}

AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation.
Haoyi Qiu, Kung-Hsiang Huang*, Jingnong Qu*, Nanyun Peng.
NAACL 2024.
PDF Bibtex Code

@inproceedings{qiu-etal-2024-amrfact,
    title = "AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation",
    author = "Haoyi Qiu and Kung-Hsiang Huang and Jingnong Qu and Nanyun Peng",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    year = "2024",
    publisher = "Association for Computational Linguistics",
}

2023

Zero-shot Faithful Factual Error Correction.
Kung-Hsiang Huang, Hou Pong Chan, Heng Ji.
ACL 2023.
PDF Bibtex Code

@inproceedings{huang-etal-2023-zero,
    title = "Zero-shot Faithful Factual Error Correction",
    author = "Huang, Kung-Hsiang  and
      Chan, Hou Pong  and
      Ji, Heng",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-long.311",
    doi = "10.18653/v1/2023.acl-long.311",
    pages = "5660--5676",
}
}

Faking Fake News for Real Fake News Detection: Propaganda-Loaded Training Data Generation
Kung-Hsiang Huang, Kathleen McKeown, Preslav Nakov, Yejin Choi, Heng Ji.
ACL 2023.
PDF Bibtex Code

@inproceedings{huang-etal-2023-faking,
    title = "Faking Fake News for Real Fake News Detection: Propaganda-Loaded Training Data Generation",
    author = "Huang, Kung-Hsiang  and
      McKeown, Kathleen  and
      Nakov, Preslav  and
      Choi, Yejin  and
      Ji, Heng",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-long.815",
    doi = "10.18653/v1/2023.acl-long.815",
    pages = "14571--14589",
    
}

SWING: Balancing Coverage and Faithfulness for Dialogue Summarization.
Kung-Hsiang Huang, Siffi Singh, Xiaofei Ma, Wei Xiao, Feng Nan, Nicholas Dingwall, William Yang Wang, Kathleen McKeown.
EACL 2023 Findings.
PDF Bibtex Code

                      @inproceedings{huang-etal-2023-swing,
                        title = "{SWING}: Balancing Coverage and Faithfulness for Dialogue Summarization",
                        author = "Huang, Kung-Hsiang  and
                          Singh, Siffi  and
                          Ma, Xiaofei  and
                          Xiao, Wei  and
                          Nan, Feng  and
                          Dingwall, Nicholas  and
                          Wang, William Yang  and
                          McKeown, Kathleen",
                        editor = "Vlachos, Andreas  and
                          Augenstein, Isabelle",
                        booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
                        month = may,
                        year = "2023",
                        address = "Dubrovnik, Croatia",
                        publisher = "Association for Computational Linguistics",
                        url = "https://aclanthology.org/2023.findings-eacl.37",
                        doi = "10.18653/v1/2023.findings-eacl.37",
                        pages = "512--525",
                    }

2022

Cross-document Misinformation Detection based on Event Graph Reasoning.
Xueqing Wu, Kung-Hsiang Huang, Yi Fung, Heng Ji
NAACL 2022.
PDF Bibtex Code

                      @inproceedings{wu-etal-2022-cross,
                          title = "Cross-document Misinformation Detection based on Event Graph Reasoning",
                          author = "Wu, Xueqing  and
                            Huang, Kung-Hsiang  and
                            Fung, Yi  and
                            Ji, Heng",
                          editor = "Carpuat, Marine  and
                            de Marneffe, Marie-Catherine  and
                            Meza Ruiz, Ivan Vladimir",
                          booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
                          month = jul,
                          year = "2022",
                          address = "Seattle, United States",
                          publisher = "Association for Computational Linguistics",
                          url = "https://aclanthology.org/2022.naacl-main.40",
                          doi = "10.18653/v1/2022.naacl-main.40",
                          pages = "543--558",
                      }

CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval.
Kung-Hsiang Huang, ChengXiang Zhai, Heng Ji.
COLING 2022.
PDF Bibtex Code

                        @inproceedings{huang-etal-2022-concrete,
                          title = "{CONCRETE}: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval",
                          author = "Huang, Kung-Hsiang  and
                            Zhai, ChengXiang  and
                            Ji, Heng",
                          booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
                          month = oct,
                          year = "2022",
                          address = "Gyeongju, Republic of Korea",
                          publisher = "International Committee on Computational Linguistics",
                          url = "https://aclanthology.org/2022.coling-1.86",
                          pages = "1024--1035",
                      }

The Battlefront of Combating Misinformation and Coping with Media Bias.
Yi R Fung, Kung-Hsiang Huang, Preslav Nakov, Heng Ji
KDD 2022 Tutorial.
PDF Bibtex

                        @inproceedings{10.1145/3534678.3542615,
                          author = {Fung, Yi R. and Huang, Kung-Hsiang and Nakov, Preslav and Ji, Heng},
                          title = {The Battlefront of Combating Misinformation and Coping with Media Bias},
                          year = {2022},
                          isbn = {9781450393850},
                          publisher = {Association for Computing Machinery},
                          address = {New York, NY, USA},
                          url = {https://doi.org/10.1145/3534678.3542615},
                          doi = {10.1145/3534678.3542615},
                          booktitle = {Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
                          pages = {4790–4791},
                          numpages = {2},
                          keywords = {computation for the social good, correcting bias and misinformation, fake news detection, misinformation characterization},
                          location = {Washington DC, USA},
                          series = {KDD '22}
                          }

2021

Document-level Entity-based Extraction as Template Generation.
Kung-Hsiang Huang, Sam Tang, Nanyun Peng.
EMNLP 2021.
PDF Bibtex Code

                        @inproceedings{huang-etal-2021-document,
                        title = "Document-level Entity-based Extraction as Template Generation",
                        author = "Huang, Kung-Hsiang  and
                          Tang, Sam  and
                          Peng, Nanyun",
                        editor = "Moens, Marie-Francine  and
                          Huang, Xuanjing  and
                          Specia, Lucia  and
                          Yih, Scott Wen-tau",
                        booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
                        month = nov,
                        year = "2021",
                        address = "Online and Punta Cana, Dominican Republic",
                        publisher = "Association for Computational Linguistics",
                        url = "https://aclanthology.org/2021.emnlp-main.426",
                        doi = "10.18653/v1/2021.emnlp-main.426",
                        pages = "5257--5269",
                    }

2020

Biomedical Event Extraction with Hierarchical Knowledge Graphs.
Kung-Hsiang Huang, Mu Yang, Nanyun Peng.
EMNLP 2020 Findings.
PDF Bibtex Code

                      @inproceedings{huang-etal-2020-biomedical,
                        title = "Biomedical Event Extraction with Hierarchical Knowledge Graphs",
                        author = "Huang, Kung-Hsiang  and
                          Yang, Mu  and
                          Peng, Nanyun",
                        editor = "Cohn, Trevor  and
                          He, Yulan  and
                          Liu, Yang",
                        booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
                        month = nov,
                        year = "2020",
                        address = "Online",
                        publisher = "Association for Computational Linguistics",
                        url = "https://aclanthology.org/2020.findings-emnlp.114",
                        doi = "10.18653/v1/2020.findings-emnlp.114",
                        pages = "1277--1285",
                        abstract = "Biomedical event extraction is critical in understanding biomolecular interactions described in scientific corpus. One of the main challenges is to identify nested structured events that are associated with non-indicative trigger words. We propose to incorporate domain knowledge from Unified Medical Language System (UMLS) to a pre-trained language model via Graph Edge-conditioned Attention Networks (GEANet) and hierarchical graph representation. To better recognize the trigger words, each sentence is first grounded to a sentence graph based on a jointly modeled hierarchical knowledge graph from UMLS. The grounded graphs are then propagated by GEANet, a novel graph neural networks for enhanced capabilities in inferring complex events. On BioNLP 2011 GENIA Event Extraction task, our approach achieved 1.41{\%} F1 and 3.19{\%} F1 improvements on all events and complex events, respectively. Ablation studies confirm the importance of GEANet and hierarchical KG.",
                    }

Service

ACL Rolling Review Area Chair

Reviewer

	2023	2022	2021
ACL	◽	◽
EMNLP	◽		◽
NAACL	◽	◽
JAIR		◽