Seungju Han

Visiting @ Allen Institute for AI

Profile Image

home / blogs / insights / CV

I am currently a visiting student researcher at Allen Institute for AI (AI2), advised by Yejin Choi. At AI2, I have also worked with Nouha Dziri, Youngjae Yu, and Jack Hessel. Previously, I received my B.S. in Electrical and Computer Engineering from Seoul National University.

I am interested in developing simple, intuitive, and scalable learning algorithms to enhance the capabilities of large language models. In recent years, I have been investigating the limitations of current LLMs, including:

  • Safety of LLMs: I developed tools to detect the harms and refusals in user-LLM interactions (WildGuard) and a novel red-teaming framework to identify and mitigate the risks of LLMs without sacrificing other capabilities (WildTeaming).
  • Visual-grounding of LLMs: I studied scalable ways to build data for training and evaluating vision-language models, for example, employing internet-scale (20 million) videos to teach vision-grounded dialogue (CHAMPAGNE) and creating challenging vision-language benchmarks that current models struggle to solve, such as understanding social norms, humor, and visual arguments.

I also worked on research and engineering at a startup (Hyperconnect; acquired by Match Group for $1.7B), focusing on problems related to open-domain conversation (diversity of responses, in-context learning, retrieval augmentation, distillation) and text-to-speech (few-shot learning) to build social chatbot products, aiming to solve people’s loneliness. Additionally, I tackled product-related ML problems like long-tail classifications.

Email: wade3han at


Please see my google scholar or semantic scholar for an up-to-date list.

selected publications

* denotes equal contribution.
  1. WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
    Seungju Han*, Kavel Rao*, Allyson Ettinger, Liwei Jiang, Bill Yuchen Lin, Nathan Lambert, Yejin Choi, and Nouha Dziri
  2. WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
    Liwei Jiang, Kavel Rao,  Seungju Han, Allyson Ettinger, Faeze Brahman, Sachin Kumar, Niloofar Mireshghallah, Ximing Lu, Maarten Sap, Yejin Choi, and Nouha Dziri
  3. EMNLP
    Reading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible Commonsense Norms
    Seungju Han, Junhyeok Kim, Jack Hessel, Liwei Jiang, Jiwan Chung, Yejin Son, Yejin Choi, and Youngjae Yu
    In Conference on Empirical Methods in Natural Language Processing (EMNLP, Oral Presentation) 2023
  4. ICCV
    CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos
    Seungju Han, Jack Hessel, Nouha Dziri, Yejin Choi, and Youngjae Yu
    In International Conference on Computer Vision (ICCV) 2023
  5. CVPR
    Disentangling Label Distribution for Long-tailed Visual Recognition
    Youngkyu Hong*,  Seungju Han*, Kwanghee Choi*, Seokjun Seo, Beomsu Kim, and Buru Chang
    In Conference on Computer Vision and Pattern Recognition (CVPR) 2021