Heejin Do

Zurich, Switzerland

heejin.do@ai.ethz.ch

I am a Postdoctoral Fellow at the ETH AI Center, ETH Zurich, mentored by Prof. Mrinmaya Sachan and Prof. April Wang, and affiliated with the LRE and PEACH labs. My research focuses on the intersection of NLP and Education, specifically investigating how AI systems can learn and reason to better facilitate human learning.

Previously, I earned my Ph.D. from the Graduate School of Artificial Intelligence at POSTECH, supervised by Prof. Gary Geunbae Lee and Yunsu Kim. I also gained industry experience at NAVER Cloud AI Lab, mentored by Sangdoo Yun. I received my B.S. in Computer Education and Data Science from Sungkyunkwan University.

news

Apr 2026	Will be giving a talk at the Zurich Language AI Meetup (April 13) as an invited speaker! 🎤
Mar 2026	Started as a Lecturer for the Introduction to AI course at UZH! 👩🏻‍🏫
Mar 2026	Paper accepted at Expert Systems with Applications (ESWA) 📄⭐️
Feb 2026	Paper accepted at EACL 2026 (Findings) 📄⭐️
Nov 2025	Paper accepted at EMNLP 2025 📄⭐️
Aug 2025	Paper accepted at ACL 2025 📄⭐️
Aug 2025	Started as a Postdoctoral Fellow at the ETH AI Center, ETH Zurich! 🎉

selected publications

ESWA
Teach-to-Reason with Scoring: Self-Explainable Rationale-Driven Multi-Trait Essay Scoring

Heejin Do, Sangwon Ryu, and Gary Geunbae Lee

Expert Systems with Applications, 2026

Abs DOI Bib URL

Multi-trait automated essay scoring (AES) systems provide a fine-grained evaluation of an essay’s diverse aspects. While they excel in scoring, prior systems fail to explain why specific trait scores are assigned. This lack of transparency leaves instructors and learners unconvinced of the AES outputs, hindering their practical use. To address this, we propose a self-explainable Rationale-Driven Multi-trait automated Essay scoring (RaDME) framework. RaDME leverages the reasoning capabilities of large language models (LLMs) by distilling them into a smaller yet effective scorer.
@article{do2026radme, title = {Teach-to-Reason with Scoring: Self-Explainable Rationale-Driven Multi-Trait Essay Scoring}, author = {Do, Heejin and Ryu, Sangwon and Lee, Gary Geunbae}, journal = {Expert Systems with Applications}, pages = {132119}, year = {2026}, doi = {10.1016/j.eswa.2026.132119}, }

ACL

Multi-Facet Blending for Faceted Query-by-Example Retrieval

Heejin Do^*, Sangwon Ryu^*, Jonghwi Kim, and 1 more author

In Proceedings of the Association for Computational Linguistics (ACL 2025), 2025

Bib URL

@inproceedings{do2025multifacet,
  title = {Multi-Facet Blending for Faceted Query-by-Example Retrieval},
  author = {Do, Heejin and Ryu, Sangwon and Kim, Jonghwi and Lee, Gary Geunbae},
  booktitle = {Proceedings of the Association for Computational Linguistics (ACL 2025)},
  year = {2025},
}

EMNLP

Leveraging What’s Overfixed: Post-Correction via LLM Grammatical Error Overcorrection

Taehee Park^*, Heejin Do^*, and Gary Geunbae Lee

In Proceedings of Empirical Methods in Natural Language Processing (EMNLP 2025), 2025

Bib URL

@inproceedings{park2025overcorrection,
  title = {Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrection},
  author = {Park, Taehee and Do, Heejin and Lee, Gary Geunbae},
  booktitle = {Proceedings of Empirical Methods in Natural Language Processing (EMNLP 2025)},
  year = {2025},
}

EMNLP

Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards

Heejin Do, Sangwon Ryu, and Gary Geunbae Lee

In Proceedings of Empirical Methods in Natural Language Processing (EMNLP 2024), 2024

Bib URL

@inproceedings{do2024autoregressive,
  title = {Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards},
  author = {Do, Heejin and Ryu, Sangwon and Lee, Gary Geunbae},
  booktitle = {Proceedings of Empirical Methods in Natural Language Processing (EMNLP 2024)},
  year = {2024},
}

ACL

Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning

Sangwon Ryu^*, Heejin Do^*, Yunsu Kim, and 2 more authors

In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), 2024

DOI Bib URL

@inproceedings{ryu-etal-2024-multi,
  title = {Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning},
  author = {Ryu, Sangwon and Do, Heejin and Kim, Yunsu and Lee, Gary and Ok, Jungseul},
  booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024)},
  year = {2024},
  pages = {5858--5871},
  doi = {10.18653/v1/2024.acl-long.319},
}

Interspeech

Score-Balanced Loss for Multi-Aspect Pronunciation Assessment

Heejin Do, Yunsu Kim, and Gary Geunbae Lee

In Proceedings of Interspeech 2023, 2023

Bib URL Code

@inproceedings{do2023score,
  title = {Score-Balanced Loss for Multi-Aspect Pronunciation Assessment},
  author = {Do, Heejin and Kim, Yunsu and Lee, Gary Geunbae},
  booktitle = {Proceedings of Interspeech 2023},
  year = {2023},
}

ACL

Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring

Heejin Do, Yunsu Kim, and Gary Geunbae Lee

In Findings of the Association for Computational Linguistics (ACL 2023), 2023

Bib URL Code

@inproceedings{do2023prompt,
  title = {Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring},
  author = {Do, Heejin and Kim, Yunsu and Lee, Gary Geunbae},
  booktitle = {Findings of the Association for Computational Linguistics (ACL 2023)},
  year = {2023},
}

ICASSP

Hierarchical Pronunciation Assessment with Multi-Aspect Attention

Heejin Do, Yunsu Kim, and Gary Geunbae Lee

In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023), 2023

Bib URL Code

@inproceedings{do2023hierarchical,
  title = {Hierarchical Pronunciation Assessment with Multi-Aspect Attention},
  author = {Do, Heejin and Kim, Yunsu and Lee, Gary Geunbae},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023)},
  year = {2023},
}