@article{do2026faithfulness,title={Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators},author={Do, Heejin and Sonkar, Shashank and Sachan, Mrinmaya},year={2026},booktitle={NeurIPS 2026},}
EMNLP Findings
SWIM: Student Writing Simulation via Proficiency-Conditioned Generation
@article{do2026swim,title={SWIM: Student Writing Simulation via Proficiency-Conditioned Generation},author={Do, Heejin and Kontak, Jakub and Sachan, Mrinmaya},booktitle={Proceedings of Empirical Methods in Natural Language Processing (EMNLP 2026)},year={2026},}
EMNLP Findings
Do LLMs Exhibit Coherent Knowledge Structures in Mathematical Reasoning? A Perspective from Knowledge Space Theory
@article{cui2026coherent,title={Do LLMs Exhibit Coherent Knowledge Structures in Mathematical Reasoning? A Perspective from Knowledge Space Theory},booktitle={Proceedings of Empirical Methods in Natural Language Processing (EMNLP 2026)},author={Cui, Peng and Do, Heejin and Sachan, Mrinmaya},year={2026},}
EMNLP
GPAgentBench-2K: Benchmarking Large Language Model Agents in Complex Clinical Action Space
@article{chen2026gpagentbench,title={GPAgentBench-2K: Benchmarking Large Language Model Agents in Complex Clinical Action Space},booktitle={Proceedings of Empirical Methods in Natural Language Processing (EMNLP 2026)},author={Chen, Boqi and Liu, Xudong and Ao, Yunke and Do, Heejin and Qiu, Jianing},year={2026},}
arxiv
Last Translation Benchmark
Vilém Zouhar, Niyati Bafna, Mukund Choudhary, Maike Züfle, Sara Rajaee, and 145 more authors
@article{vilem2026last,title={Last Translation Benchmark},author={Zouhar, Vilém and Bafna, Niyati and Choudhary, Mukund and Züfle, Maike and Rajaee, Sara and Chen, Pinzhen and Vamvas, Jannis and Papi, Sara and de Gibert, Ona and Malik, Bhavitvya and Habba, Eliya and Mastromichalakis, Orfeas Menis and Schmidtová, Patrícia and Wastl, Michelle and Issaka, Sheriff and Choshen, Leshem and Biderman, Stella and Anastasopoulos, Antonis and Niehues, Jan and Sennrich, Rico and Sachan, Mrinmaya and Bojar, Ondřej and Murray, Kenton and Tiedemann, Jörg and Aji, Alham Fikri and Koehn, Philipp and Monz, Christof and Birch, Alexandra and Vajjala, Sowmya and Kranti, Chalamalasetti and España-Bonet, Cristina and Sarwar, Nobin and Kaczér, David and Asano, Shunta and Marmonier, Malik and Jaff, Daban Q and Mishra, Vaisakhi and Khalifa, Hend Al and Sarti, Gabriele and Saha, Sourajit and Rehlinger, Nils and Villa, Juan Daniel Cuervo and Tonglet, Jonathan and Purkayastha, Saugata and Macháček, Dominik and Ramanujam, Jagannathan and Do, Heejin and Nadova, Zuzana and Philippy, Fred and Retkowski, Fabian and Lymperaiou, Maria and Casola, Silvia and Yukhymenko, Hanna and Dipta, Shubhashis Roy and Ryu, Sangwon and Jerez, Andrés and Keinan, Ron and Yusuf, Shuaib Shuaib and Vempati, Avantica and Staiano, Maria Carmen and Purkayastha, Sukannya and Cosma, Adrian and Babenko, Vitalii and Inan, Erivan and Nigam, Aviral and Aissa, Wafa and Haouari, Fatima and Gummadi, Venkata Prasanth Kumar and Jafarzadeh, Mehdi and Scourneau, Valentin and Edman, Lukas and Sun, Kaiser and Tan, Shaomu and Gholizadeh, Mohammad Sadegh and David, Johannes-Rudolf and Srirag, Dipankar and Gilabert, Javier García and Binkyte, Ruta and Ali, Manar and Bucur, Ana-Maria and Farrag, Sabry E and Saber, Youssef and Liu, Yihong and Maillard, Jean and Nicoleta, Cojocaru and Yuan, Xiaochuang and Ahmadi, Sina and Mondorf, Philipp and Dhole, Kaustubh and Wixinger, Roman and Qian, Shenbin and Tuor, Manuel and Troshin, Sergey and Yahav, Jonathan and Thoker, Fida Mohammad and Rezapour, Amir Arsalan and Gamboa, Lance Calvin Lim and Reusens, Manon and Kukk, Kätriin and Chowdhury, Koel Dutta and Gallipoli, Giuseppe and Hoang, Christian and Saha, Shaswati and Aycock, Seth and Kocoń, Jan and Chen, Bo and Vu, Linh and Venkatkrishna, Vatsal and Ahsan, Arafat and Nguyen, Luan Thanh and Soliman, Hassan and Dementieva, Daryna and Rampisela, Theresia Veronika and Do, Ngoc Quynh Tram and Huber, Marius and Egashira, Kazuki and Wasi, Azmine Toushik and Poritski, Vladislav and Zhang, Mike and Shah, Deep and Gavrikov, Paul and Salim, Luis Frentzen and Africa, David and Damanhuri, R and Bello, Bello Umar and Garg, Anumit and Rao, Gengyu and Ammanamanchi, Pawan Sasanka and Dementaviciute, Kamile and Michail, Andrianos and Teja, LDMS and Zhu, Dawei and Fan, Yi and Liu, Wei and Farsi, Farhan and Herranen, Elias and Chowdhury, Sankalan Pal and Sanchez, Karen and Shami, Farzad and Urlana, Ashok and Wang, Zimu and Limisiewicz, Tomasz and Pattnayak, Priyaranjan and Ojastu, Marii and Na, Hongbin and Radoi, Emilian and Zhao, Chenyi and Hinojosa, Carlos and de Varda, Andrea Gregor and Alyafeai, Zaid},year={2026},}
SIGCSE
Exploring the Role of Tracing in AI-Supported Planning for Algorithmic Reasoning
Yoshee Jain, Heejin Do, Zihan Wu, and April Yi Wang
@article{jain2026tracing,title={Exploring the Role of Tracing in AI-Supported Planning for Algorithmic Reasoning},author={Jain, Yoshee and Do, Heejin and Wu, Zihan and Wang, April Yi},year={2026},booktitle={ACM Special Interest Group on Computer Science Education (SIGCSE) 2026},}
Under Review
NL2Scratch: An Executable Benchmark and Evaluation for Block-Based Programming
Heejin Do, Alexandre Ballenghien, Yang Wu, and April Yi Wang
@article{donl2scratch,title={NL2Scratch: An Executable Benchmark and Evaluation for Block-Based Programming},author={Do, Heejin and Ballenghien, Alexandre and Wu, Yang and Wang, April Yi},year={2026},booktitle={Under Review},}
Under Review
Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education
Junling Wang, Boqi Chen, Heejin Do, Mubashara Akhtar, April Yi Wang, and 1 more author
@article{wang2026,title={Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education},author={Wang, Junling and Chen, Boqi and Do, Heejin and Akhtar, Mubashara and Wang, April Yi and Sachan, Mrinmaya},year={2026},booktitle={Under Review},}
Interspeech
Segment-level Tree Search for Long Meeting Document Summarization
Sangwon Ryu, Heejin Do, Jun Seo, Daehui Kim, Yunsu Kim, and 2 more authors
@article{ryuinterspeech2026,title={Segment-level Tree Search for Long Meeting Document Summarization},author={Ryu, Sangwon and Do, Heejin and Seo, Jun and Kim, Daehui and Kim, Yunsu and Lee, Gary Geunbae and Ok, Jungseul},year={2026},booktitle={Interspeech 2026},}
ACL
Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
Sangwon Ryu, Heejin Do, Yunsu Kim, Gary Lee, and Jungseul Ok
In Proceedings of the Association for Computational Linguistics (ACL 2026), 2026
@inproceedings{ryu2026adaptive,title={Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search},author={Ryu, Sangwon and Do, Heejin and Kim, Yunsu and Lee, Gary and Ok, Jungseul},booktitle={Proceedings of the Association for Computational Linguistics (ACL 2026)},year={2026},}
ACL Findings
Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
Jun Seo, Sangwon Ryu, Heejin Do†, Hyounghun Kim, and Gary Geunbae Lee†
In Findings of the Association for Computational Linguistics (ACL 2026), 2026
@inproceedings{seo2026behavior,title={Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing},author={Seo, Jun and Ryu, Sangwon and Do, Heejin and Kim, Hyounghun and Lee, Gary Geunbae},booktitle={Findings of the Association for Computational Linguistics (ACL 2026)},year={2026},}
ESWA
Teach-to-Reason with Scoring: Self-Explainable Rationale-Driven Multi-Trait Essay Scoring
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},}
EACL Findings
Exploring Iterative Controllable Summarization with Large Language Models
Sangwon Ryu, Heejin Do, Daehui Kim, Hwanjo Yu, Dongwoo Kim, and 3 more authors
In Findings of the Association for Computational Linguistics (EACL 2026), 2026
@inproceedings{ryu2026iterative,title={Exploring Iterative Controllable Summarization with Large Language Models},author={Ryu, Sangwon and Do, Heejin and Kim, Daehui and Yu, Hwanjo and Kim, Dongwoo and Kim, Yunsu and Lee, Gary and Ok, Jungseul},booktitle={Findings of the Association for Computational Linguistics (EACL 2026)},year={2026},}
2025
Under Review
What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation
@article{do2025reasoning,title={What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation},author={Do, Heejin and Hwang, Jaehui and Han, Dongyoon and Oh, Seong Joon and Yun, Sangdoo},year={2025},booktitle={Under Review},}
ACL
Multi-Facet Blending for Faceted Query-by-Example Retrieval
Heejin Do*, Sangwon Ryu*, Jonghwi Kim, and Gary Geunbae Lee
In Proceedings of the Association for Computational Linguistics (ACL 2025), 2025
@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
@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},}
NAACL Findings
Towards Prompt Generalization: Grammar-aware Cross-Prompt Automated Essay Scoring
Heejin Do, Taehee Park, Sangwon Ryu, and Gary Geunbae Lee
In Findings of the Association for Computational Linguistics (NAACL 2025), 2025
@inproceedings{do2025grammar,title={Towards Prompt Generalization: Grammar-aware Cross-Prompt Automated Essay Scoring},author={Do, Heejin and Park, Taehee and Ryu, Sangwon and Lee, Gary Geunbae},booktitle={Findings of the Association for Computational Linguistics (NAACL 2025)},year={2025},}
NAACL
Multimodal Cognitive Reframing Therapy via Multi-hop Psychotherapeutic Reasoning
Subin Kim, Hoonrae Kim, Heejin Do, and Gary Lee
In Proceedings of the Nations of the Americas Chapter of ACL (NAACL 2025), 2025
@inproceedings{kim2025cognitive,title={Multimodal Cognitive Reframing Therapy via Multi-hop Psychotherapeutic Reasoning},author={Kim, Subin and Kim, Hoonrae and Do, Heejin and Lee, Gary},booktitle={Proceedings of the Nations of the Americas Chapter of ACL (NAACL 2025)},year={2025},}
NAACL
DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition
Wonjun Lee, Solee Im, Heejin Do, Yunsu Kim, Jungseul Ok, and 1 more author
In Proceedings of the Nations of the Americas Chapter of ACL (NAACL 2025), 2025
@inproceedings{lee2025dypcl,title={DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition},author={Lee, Wonjun and Im, Solee and Do, Heejin and Kim, Yunsu and Ok, Jungseul and Lee, Gary},booktitle={Proceedings of the Nations of the Americas Chapter of ACL (NAACL 2025)},year={2025},}
NAACL
Revisiting Early Detection of Sexual Predators via Turn-level Optimization
Jinmyeong An, Sangwon Ryu, Heejin Do, Yunsu Kim, Jungseul Ok, and 1 more author
In Proceedings of the Nations of the Americas Chapter of ACL (NAACL 2025), 2025
@inproceedings{an2025predator,title={Revisiting Early Detection of Sexual Predators via Turn-level Optimization},author={An, Jinmyeong and Ryu, Sangwon and Do, Heejin and Kim, Yunsu and Ok, Jungseul and Lee, Gary},booktitle={Proceedings of the Nations of the Americas Chapter of ACL (NAACL 2025)},year={2025},}
2024
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
@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},}
Interspeech
Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment
@inproceedings{do24_interspeech,title={Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment},author={Do, Heejin and Lee, Wonjun and Lee, Gary Geunbae},booktitle={Interspeech 2024},year={2024},pages={312--316},doi={10.21437/Interspeech.2024-2498},}
Interspeech
Key-Element-Informed sLLM Tuning for Document Summarization
Sangwon Ryu*, Heejin Do*, Yunsu Kim, Gary Geunbae Lee, and Jungseul Ok
@inproceedings{ryu24_interspeech,title={Key-Element-Informed sLLM Tuning for Document Summarization},author={Ryu, Sangwon and Do, Heejin and Kim, Yunsu and Lee, Gary Geunbae and Ok, Jungseul},booktitle={Interspeech 2024},year={2024},pages={1940--1944},doi={10.21437/Interspeech.2024-2389},}
ACL
Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning
Sangwon Ryu*, Heejin Do*, Yunsu Kim, Gary Lee, and Jungseul Ok
In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), 2024
@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},}
AIED
Aspect-based Semantic Textual Similarity for Educational Test Items
Heejin Do and Gary Geunbae Lee
In Proceedings of International Conference on Artificial Intelligence in Education (AIED 2024), 2024
@inproceedings{do2024aspect,title={Aspect-based Semantic Textual Similarity for Educational Test Items},author={Do, Heejin and Lee, Gary Geunbae},booktitle={Proceedings of International Conference on Artificial Intelligence in Education (AIED 2024)},year={2024},}
EACL Findings
Autoregressive Score Generation for Multi-trait Essay Scoring
Heejin Do, Yunsu Kim, and Gary Geunbae Lee
In Findings of the European Chapter of the Association for Computational Linguistics (EACL 2024), 2024
@inproceedings{do2024autoregressive_score,title={Autoregressive Score Generation for Multi-trait Essay Scoring},author={Do, Heejin and Kim, Yunsu and Lee, Gary Geunbae},booktitle={Findings of the European Chapter of the Association for Computational Linguistics (EACL 2024)},year={2024},}
2023
Interspeech
Score-Balanced Loss for Multi-Aspect Pronunciation Assessment
@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 Findings
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
@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
@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},}
2022
TALLIP
Target-Oriented Knowledge Distillation with Language-Family-Based Grouping for Multilingual NMT
Heejin Do and Gary Geunbae Lee
ACM Transactions on Asian and Low-Resource Language Information Processing, 2022
@article{do2022target,title={Target-Oriented Knowledge Distillation with Language-Family-Based Grouping for Multilingual NMT},author={Do, Heejin and Lee, Gary Geunbae},journal={ACM Transactions on Asian and Low-Resource Language Information Processing},year={2022},}