Seonghyeon Ye
KAIST Graduate school of AI
Hello, I am a second year Ph.D student in KAIST Graduate school of AI. I am advised by Professor Minjoon Seo and a member of LKLab (Language & Knowledge Lab).
I am currently interested in making Large Language Models (LLMs) follow human instructions. Recently, I am trying to make LLMs as policies for general low-level embodied tasks.
Publications
2024
FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
Seonghyeon Ye*, Doyoung Kim*, Sungdong Kim, Hyeonbin Hwang, Seungone Kim, Yongrae Jo, James Thorne, Juho Kim, Minjoon Seo ( * denotes equal contribution)
ICLR 2024 (Spotlight)
[paper][code]
Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis
Sohee Yang, Jonghyeon Kim, Joel Jang, Seonghyeon Ye, Hyunji Lee, Minjoon Seo
TACL 2024
[paper][code]
Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following
Seonghyeon Ye, Hyeonbin Hwang, Sohee Yang, Hyeongu Yun, Yireun Kim, Minjoon Seo
AAAI 2024
[paper][code]
2023
Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models
Yujin Kim, Jaehong Yoon, Seonghyeon Ye, Sung Ju Hwang, Se-young Yun
Syntheticdata4ML Workshop @ NeurIPS 2023 (Oral)
[paper]
The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-tuning
Seungone Kim, Se June Joo, Doyoung Kim, Joel Jang, Seonghyeon Ye, Jamin Shin, Minjoon Seo
EMNLP 2023
[paper][code]
Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt
Seonghyeon Ye, Joel Jang, Doyoung Kim, Yongrae Jo, Minjoon Seo
EMNLP 2023 Findings
[paper][code]
Exploring the Benefits of Training Expert Language Models over Instruction Tuning
Joel Jang, Seungone Kim, Seonghyeon Ye, Doyoung Kim, Lajanugen Logeswaran, Moontae Lee, Kyungjae Lee, Minjoon Seo
ICML 2023
[paper][code]
Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners
Seonghyeon Ye, Doyoung Kim, Joel Jang, Joongbo Shin, Minjoon Seo
ICLR 2023
[paper][code][demo]
SelFee: Iterative Self-Revising LLM Empowered by Self-Feedback Generation
Seonghyeon Ye*, Yongrae Jo*, Doyoung Kim*, Sungdong Kim, Hyeonbin Hwang, Minjoon Seo ( * denotes equal contribution)
Blog post
[blog][code]
2022
Can Large Language Models Truly Understand Prompts? A Case Study with Negated Prompts
Joel Jang*, Seonghyeon Ye*, Minjoon Seo ( * denotes equal contribution)
Transfer Learning for NLP Workshop @ NeurIPS 2022
[paper][code]
TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models
Joel Jang*, Seonghyeon Ye*, Chango Lee, Sohee Yang, Joongbo Shin, Janghoon Han, Gyeonghun Kim, Minjoon Seo ( * denotes equal contribution)
EMNLP 2022
[paper][code]
Towards Continual Knowledge Learning of Language Models
Joel Jang, Seonghyeon Ye, Sohee Yang, Joongbo Shin, Janghoon Han, Gyeonghun Kim, Stanley Jungkyu Choi, Minjoon Seo
ICLR 2022
[paper][code]
2021
Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning
Seonghyeon Ye, Jiseon Kim, Alice Oh
EMNLP 2021 (short)
[paper] [code]
Dimensional Emotion Detection from Categorical Emotion
Sungjoon Park, Jiseon Kim, Seonghyeon Ye, Jaeyeol Jeon, Hee Young Park, Alice Oh
EMNLP 2021
[paper] [code]
Education
| Mar 2022 - Present | KAIST Graduate School of AI |
|---|---|
| Mar 2017 - Aug 2021 | KAIST B.S School of Computing |
Academic Services
Reviewer : EMNLP 2022, ICLR 2023, ACL 2023, NeurIPS 2023, EMNLP 2023, ICLR 2024
Work Experience
| Jul 2022 - Mar 2023 |
LG AI Research (Research Intern)
Host : Joongbo Shin |
|---|---|
| Jul 2021 - Feb 2022 |
LKLab (Research Intern)
Host : Minjoon Seo |
| Jul 2020 - Jun 2020 |
U&I Lab (Research Intern)
Host : Alice Oh |
| Dec 2019 - Feb 2020 | ELICE (Frontend Engineer) |
Teaching Experience
Spring
2021
CS101 Introduction to Programming
| Spring 2021 | CS101 Introduction to Programming |
|---|