Joongwon (Daniel) Kim

I am a third-year Ph.D. student in the Natural Language Processing group at the University of Washington, and a visiting researcher at Meta AI. I am thankful to be advised by Hannaneh Hajishirzi. Previously, I was an undergrad at the University of Pennsylvania, working with Chris Callison-Burch and Mark Yatskar.

My current research interest focuses on improving LLM capabilities for addressing complex reasoning tasks via 1) building synthetic data generation pipelines, 2) applying advanced search/planning algorithms and 3) integrating tool use abilities. I am also supported by the NSF-GRFP Fellowship.

News

• 09/2024: I am staying at Meta as a visiting researcher while continuing my PhD.
• 06/2024: I have started working in the Llama team at Meta Gen AI for the summer!
• 06/2024: Our work Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning has been released!
• 10/2023: Our work TaskWeb: Selecting Better Source Tasks for Multi-task NLP has been accepted to EMNLP 2023! New version coming soon.
• 05/2023: Our new preprint TaskWeb: Selecting Better Source Tasks for Multi-task NLP has been released!
• 09/2022: I begin my Ph.D. at the University of Washington!
• 04/2022: I have been awarded the NSF-GRFP Fellowship (2022-27).
• 03/2022: I have been awarded the CSE Educators' Endowed Fellowship in Computer Science & Engineering from the Allen School.
• 12/2021: I have been selected for honorable mentions for the CRA Outstanding Undergraduate Researcher Awards 2022.

CV  /  Email  /  GitHub  /  Google Scholar  /  Twitter

We introduce Husky, an open-source language agent that learns to reason over a unified action space to address multi-step tasks involving numerical, tabular, and knowledge-based reasoning. Our experiments show that Husky outperforms prior language agents across 14 evaluation sets. Moreover, we present new evaluation sets that require mixed-tool reasoning and show that Husky matches or even exceeds frontier LMs such as GPT-4 on these tasks despite only using 7B models.

We introduce TaskWeb, our benchmark of pairwise task transfers between 22 different NLP tasks across three different model types, sizes and adaptation method. Based on TaskWeb, we propose a new method TaskShop for estimating transferability between source and target tasks with only a small number of target examples. We demonstrate that selecting helpful source tasks with our method allows us to perform multi-task learning on much smaller training sets and still improve zero-shot performance across various target tasks.

We built schemas for goal-oriented tasks by aligning YouTube videos with wikiHow steps. Then, we proposed methods for editing the schemas to handle unseen but related tasks. Finally, we leveraged our schemas to perform instructional video retrieval on several datasets and demonstrated that our method improves over other retrieval approaches.

We curated a multilingual corpus for sentence splitting by using machine translation over parallel corpora. Moreover, we developed a sentence splitter with controllable generation. We showed that our dataset and model outperformed existing methods in both automatic and human evaluations. Work done in collaboration with Georgia Tech.

Website source from Jon Barron