Hello, I’m a 2nd year Stanford Masters of Computer Science student.

My areas of interest are pluralistic alignment, personalization, post-training via RL and representation learning with Large Language Models (LLMs).

Before coming to Stanford, I have experience in Alexa, AWS AI teams.

Here is my CV.

I personally organize a weekly NLP study group for Korean industry professionals and upcoming researchers. Please feel free to shoot an email if you’d like to join!

Publications

Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings

Published in ACL (to appear), 2026

Minsik Oh, Jiwei Li, Guoyin Wang. [Paper]

Steerable Preference Optimization of Reward Models

Published in review, 2025

Minsik Oh, Advit Deepak, Sophie Wu, Douwe Kiela, Ekaterina Shutova [Paper]

Continual Pre-Training for Hallucination Reduction

Published in review, 2025

Minsik Oh, Sungju Kim, Douwe Kiela, Guoyin Wang, Kang Min Yoo, Joosung Lee [Paper]

Dynamic Summarization Length Control via Model Merging

Published in review, 2025

Mehmet Hamza Erol*, Minsik Oh*, Douwe Kiela [Paper]

PK-ICR: Persona-Knowledge Interactive Context Retrieval for Grounded Dialogue

Published in EMNLP Main Conference (Oral), 2023

Minsik Oh, Joosung Lee, Jiwei Li, Guoyin Wang. [Paper]

P5: Plug-and-Play Persona Prompting for Personalized Response Selection

Published in EMNLP Main Conference, 2023

Joosung Lee, Minsik Oh, Donghun Lee. [Paper]

Template-augmented Dialogue Representation Learning

Published in Workshop on Knowledge Augmented Methods for NLP, AAAI, 2023

Minsik Oh, Guoyin Wang, Taiwoo Park, Puyang Xu. [Paper] [Poster]

Persona-Knowledge Dialogue Multi-Context Retrieval and Enhanced Decoding Methods

Published in The 1st Workshop on Customized Chat Grounding Persona and Knowledge, COLING, 2022

Minsik Oh*, Minsang Kim*. [Paper]

NEAMER - Named Entity Augmented Multi-word Expression Recognizer

Published in Proceedings of the 16th International Workshop on Semantic Evaluation, NAACL, 2022

Minsik Oh. [Paper]