18
presentations
8
number of views
SHORT BIO
Chanjun Park is a Research Professor at Korea University. Before joining Korea University, he served as a Principal Research Engineer and Technical Leader for the Large Language Models (LLMs) team at Upstage, where he contributed to building an ecosystem for LLMs. He also worked as a Research Engineer at SYSTRAN, contributing to the development of machine translation (MT) and automatic speech recognition (ASR) systems. He earned his Ph.D. at Korea University under the supervision of Professor Heuiseok Lim. He has authored over 100 publications in leading NLP conferences and journals, such as ACL, EMNLP, NAACL, EACL, and COLING. He has delivered over 70 invited talks and has significant teaching experience. Additionally, he holds more than 10 patents in the field of natural language processing (NLP). His achievements include recognition in Forbes 30 Under 30 Korea in the SCIENCE / SW field and the Naver Ph.D. Fellowship. He has been actively involved in the academic community, holding roles such as Virtual Social Chair at COLING 2022, Publication Chair for DMLR at ICLR 2024, and Program Chair for the WiNLP Workshop.
Presentations
Where am I? Large Language Models Wandering between Semantics and Structures in Long Contexts
Seonmin Koo and 4 other authors
Translation of Multifaceted Data without Re-Training of Machine Translation Systems
Hyeonseok Moon and 5 other authors
SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models
Hyeonwoo Kim and 6 other authors
Search if you don't know! Knowledge-Augmented Korean Grammatical Error Correction with Large Language Models
Seonmin Koo and 3 other authors
KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models
Jaehyung Seo and 5 other authors
Length-aware Byte Pair Encoding for Mitigating Over-segmentation in Korean Machine Translation
Jungseob Lee and 8 other authors
Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmark
Chanjun Park and 7 other authors
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up
Chanjun Park and 5 other authors
Explainable CED: A Dataset for Explainable Critical Error Detection in Machine Translation
Dahyun Jung and 3 other authors
Exploring Inherent Biases in LLMs within Korean Social Context: A Comparative Analysis of ChatGPT and GPT-4
Seungyoon Lee and 4 other authors
Hyper-BTS Dataset: Scalability and Enhanced Analysis of Back TranScription (BTS) for ASR Post-Processing
Chanjun Park and 7 other authors
Generative Interpretation: Toward Human-Like Evaluation for Educational Question-Answer Pair Generation
Hyeonseok Moon and 5 other authors
CHEF in the Language Kitchen: A Generative Data Augmentation Leveraging Korean Morpheme Ingredients
Jaehyung Seo and 5 other authors
KEBAP: Korean Error Explainable Benchmark Dataset for ASR and Post-processing | VIDEO
Seonmin Koo and 6 other authors
Informative Evidence-guided Prompt-based Fine-tuning for English-Korean Critical Error Detection
Dahyun Jung and 5 other authors
PicTalky: Augmentative and Alternative Communication for Language Developmental Disabilities
Chanjun Park