Jaehun Jung

I'm a Ph.D student in computer science at the University of Washington, advised by Yejin Choi.

My research focuses on how to train and evaluate a model with a model, with minimal human supervision. I am specifically excited in
  • Data Generation & Selection using Language Models
  • Improving Reliability and Controllability of Language Models
  • LLM-based Reasoning
  • Behavioral Analysis of LLMs

Previously I was an undergrad at Seoul National University, advised by Professor U Kang and Jinwook Seo. I was also a part-time researcher in Kakao Enterprise, where I worked on knowledge-grounded dialogue agents.

Email  /  CV  /  Scholar  /  Twitter  /  Github

profile photo

Research

Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
Jaehun Jung, Faeze Brahman, Yejin Choi
preprint, 2024
paper / bibtex

We enhance LLM judges with a statistically rigorous guarantee of human agreement. We further extend this guarantee to propose Cascaded Selective Evaluation, where we start from a small cost-effective model as a judge, and escalate to a stronger model only when necessary—all while guaranteeing high agreement with humans.

Information-Theoretic Distillation for Reference-less Summarization
Jaehun Jung, Ximing Lu, Liwei Jiang, Faeze Brahman, Peter West, Pang Wei Koh, Yejin Choi
COLM, 2024
paper / bibtex

Can small models excel at summarization without imitating LLM or human-written references? We present InfoSumm, a framework to distill a powerful summarizer that outperforms order-of-magnitude larger LLM summarizers, solely based on the information-theoretic objective for summarization.

Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Models
Jaehun Jung, Peter West, Liwei Jiang, Faeze Brahman, Ximing Lu, Jillian Fisher, Taylor Sorensen, Yejin Choi
NAACL, 2024
paper / data / bibtex

It is possible to generate a high-quality dataset for sentential paraphrasing and summarization directly from an off-the-shelf LM, even when it is impossible for the LM itself to reliably perform these tasks.

Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
Jillian Fisher, Ximing Lu, Jaehun Jung, Liwei Jiang, Zaid Harchaoui, Yejin Choi
NAACL, 2024 (Oral Presentation)
paper / github / bibtex

We introduce JamDec, an inference-time algorithm for authorship obfuscation that is domain-agnostic, controllable, yet does not require human supervision.

Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
Ximing Lu, Faeze Brahman, Peter West, Jaehun Jung, ..., Xiang Ren, Sean Welleck, Yejin Choi
EMNLP, 2023
paper / github / bibtex

Can we adapt LLMs without fine-tuning? We propose using a lightweight adapter (e.g. GPT-2) during decoding time, efficiently tailoring even the strongest proprietary LLMs toward user-defined reward.

STEER: Unified Style Transfer with Expert Reinforcement
Skyler Hallinan, Faeze Brahman, Ximing Lu, Jaehun Jung, Sean Welleck, Yejin Choi
Findings of EMNLP, 2023
paper / github / bibtex

We propose a text style transfer framework from arbitrary source style to many target styles via large-scale data generation with expert-guided decoding and offline RL.

Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations
Jaehun Jung, Lianhui Qin, Sean Welleck, Faeze Brahman, Chandra Bhagavatula, Ronan Le Bras, Yejin Choi
EMNLP, 2022 (Oral Presentation)
paper / github / bibtex

We improve LM reasoning by generating abductive and recursive explanations from language models, then formulating inference as a satisfiability problem over these generations.

Learning to Walk across Time for Interpretable Temporal Knowledge Graph Completion
Jaehun Jung, Jinhong Jung, U Kang
KDD, 2021
paper / github / bibtex

A novel GNN for temporal KG is proposed that encodes an interpretable graph substructure for knowledge graph completion.

AttnIO: Knowledge Graph Exploration with In-and-Out Attention Flow for Knowledge-Grounded Dialogue
Jaehun Jung, Bokyung Son, Sungwon Lyu
EMNLP, 2020
paper / video / bibtex

We present a novel decoder model based on attention flow that learns to explore KG and retrieve a relevant knowledge path to ground a dialogue agent.

DataHalo: A Customizable Notification Visualization System for Personalized and Longitudinal Interactions
Guhyun Han, Jaehun Jung, Youngho Kim Jinwook Seo
CHI, 2023
paper / bibtex

DataHalo implements a customizable notification visualization system for mobile devices, providing prolonged ambient visualizations based on time-varying importance model to enable longitudinal interaction with the notifications.




Website design by Jon Barron