Jaewook Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jaewook Lee has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Andrew Lan
University of Massachusetts Amherst
5 shared publications Andrew Lan
University of Massachusetts Amherst
3 shared publications- Alexander Scarlatos
University of Massachusetts Amherst 2 Eedi
2 shared publications - Hunter McNichols
University of Massachusetts Amherst
2 shared publications - Alexander Scarlatos
University of Massachusetts Amherst
1 shared publication Jeongah Lee
University of Massachusetts Amherst
1 shared publication
Latest Publications
- Open Access
Letting Tutor Personas "Speak Up" for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization
With the emergence of large language models (LLMs) as a powerful class of generative artificial intelligence (AI), their use in tutoring has become increasingly prominent. Prior works on LLM-based tutoring typically learn a single tutor policy and do not capture the diversity of tutoring styles. In real-world tutor-student interactions, pedagogical intent is realized through adaptive instructional strategies, with tutors varying the level of scaffolding, instructional directiveness, feedback, and affective support in response to learners' needs. These differences can all impact dialogue dynamics and student engagement. In this paper, we explore how tutor personas embedded in human tutor-student dialogues can be used to guide LLM behavior without relying on explicitly prompted instructions. We modify Bidirectional Preference Optimization (BiPO) to learn a steering vector, an activation-space direction that steers model responses towards certain tutor personas. We find that this steering vector captures tutor-specific variation across dialogue contexts, improving semantic alignment with ground-truth tutor utterances and increasing preference-based evaluations, while largely preserving lexical similarity. Analysis of the learned directional coefficients further reveals interpretable structure across tutors, corresponding to consistent differences in tutoring behavior. These results demonstrate that activation steering offers an effective and interpretable way for controlling tutor-specific variation in LLMs using signals derived directly from human dialogue data.
Open AccessLetting Tutor Personas "Speak Up" for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization
With the emergence of large language models (LLMs) as a powerful class of generative artificial intelligence (AI), their use in tutoring has become increasingly prominent. Prior works on LLM-based tutoring typically learn a single tutor policy and do not capture the diversity of tutoring styles. In real-world tutor-student interactions, pedagogical intent is realized through adaptive instructional strategies, with tutors varying the level of scaffolding, instructional directiveness, feedback, and affective support in response to learners' needs. These differences can all impact dialogue dynamics and student engagement. In this paper, we explore how tutor personas embedded in human tutor-student dialogues can be used to guide LLM behavior without relying on explicitly prompted instructions. We modify Bidirectional Preference Optimization (BiPO) to learn a steering vector, an activation-space direction that steers model responses towards certain tutor personas. We find that this steering vector captures tutor-specific variation across dialogue contexts, improving semantic alignment with ground-truth tutor utterances and increasing preference-based evaluations, while largely preserving lexical similarity. Analysis of the learned directional coefficients further reveals interpretable structure across tutors, corresponding to consistent differences in tutoring behavior. These results demonstrate that activation steering offers an effective and interpretable way for controlling tutor-specific variation in LLMs using signals derived directly from human dialogue data.
- 20 July 2025
- Published by Springer Nature
- p. 336-349
From Text to Visuals: Using LLMs to Generate Math Diagrams with Vector Graphics
- 20 July 2025
- Published by Springer Nature
- p. 336-349
From Text to Visuals: Using LLMs to Generate Math Diagrams with Vector Graphics
- Top Cited Papers
- 15 July 2025
- Published by Springer Nature
- p. 251-266
Training LLM-Based Tutors to Improve Student Learning Outcomes in Dialogues
- 15 July 2025
- Published by Springer Nature
- p. 251-266
Top Cited PapersTraining LLM-Based Tutors to Improve Student Learning Outcomes in Dialogues
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 25465-25486
Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization
Jaewook Lee, Alexander Scarlatos, Andrew Lan. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 25465-25486
Open AccessInterpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization
Jaewook Lee, Alexander Scarlatos, Andrew Lan. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
Exploring Automated Keyword Mnemonics Generation with Large Language Models via Overgenerate-and-Rank
In this paper, we study an under-explored area of language and vocabulary learning: keyword mnemonics, a technique for memorizing vocabulary through memorable associations with a target word via a verbal cue. Typically, creating verbal cues requires extensive human effort and is quite time-consuming, necessitating an automated method that is more scalable. We propose a novel overgenerate-and-rank method via prompting large language models (LLMs) to generate verbal cues and then ranking them according to psycholinguistic measures and takeaways from a pilot user study. To assess cue quality, we conduct both an automated evaluation of imageability and coherence, as well as a human evaluation involving English teachers and learners. Results show that LLM-generated mnemonics are comparable to human-generated ones in terms of imageability, coherence, and perceived usefulness, but there remains plenty of room for improvement due to the diversity in background and preference among language learners.
Open AccessExploring Automated Keyword Mnemonics Generation with Large Language Models via Overgenerate-and-Rank
In this paper, we study an under-explored area of language and vocabulary learning: keyword mnemonics, a technique for memorizing vocabulary through memorable associations with a target word via a verbal cue. Typically, creating verbal cues requires extensive human effort and is quite time-consuming, necessitating an automated method that is more scalable. We propose a novel overgenerate-and-rank method via prompting large language models (LLMs) to generate verbal cues and then ranking them according to psycholinguistic measures and takeaways from a pilot user study. To assess cue quality, we conduct both an automated evaluation of imageability and coherence, as well as a human evaluation involving English teachers and learners. Results show that LLM-generated mnemonics are comparable to human-generated ones in terms of imageability, coherence, and perceived usefulness, but there remains plenty of room for improvement due to the diversity in background and preference among language learners.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5521-5542
Exploring Automated Keyword Mnemonics Generation with Large Language Models via Overgenerate-and-Rank
Jaewook Lee, Hunter McNichols, Andrew Lan. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5521-5542
Open AccessExploring Automated Keyword Mnemonics Generation with Large Language Models via Overgenerate-and-Rank
Jaewook Lee, Hunter McNichols, Andrew Lan. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- 26 June 2023
- Published by Springer Nature
- p. 16-27
SmartPhone: Exploring Keyword Mnemonic with Auto-generated Verbal and Visual Cues
- 26 June 2023
- Published by Springer Nature
- p. 16-27
SmartPhone: Exploring Keyword Mnemonic with Auto-generated Verbal and Visual Cues
- Open Access
SmartPhone: Exploring Keyword Mnemonic with Auto-generated Verbal and Visual Cues
In second language vocabulary learning, existing works have primarily focused on either the learning interface or scheduling personalized retrieval practices to maximize memory retention. However, the learning content, i.e., the information presented on flashcards, has mostly remained constant. Keyword mnemonic is a notable learning strategy that relates new vocabulary to existing knowledge by building an acoustic and imagery link using a keyword that sounds alike. Beyond that, producing verbal and visual cues associated with the keyword to facilitate building these links requires a manual process and is not scalable. In this paper, we explore an opportunity to use large language models to automatically generate verbal and visual cues for keyword mnemonics. Our approach, an end-to-end pipeline for auto-generating verbal and visual cues, can automatically generate highly memorable cues. We investigate the effectiveness of our approach via a human participant experiment by comparing it with manually generated cues.
Open AccessSmartPhone: Exploring Keyword Mnemonic with Auto-generated Verbal and Visual Cues
In second language vocabulary learning, existing works have primarily focused on either the learning interface or scheduling personalized retrieval practices to maximize memory retention. However, the learning content, i.e., the information presented on flashcards, has mostly remained constant. Keyword mnemonic is a notable learning strategy that relates new vocabulary to existing knowledge by building an acoustic and imagery link using a keyword that sounds alike. Beyond that, producing verbal and visual cues associated with the keyword to facilitate building these links requires a manual process and is not scalable. In this paper, we explore an opportunity to use large language models to automatically generate verbal and visual cues for keyword mnemonics. Our approach, an end-to-end pipeline for auto-generating verbal and visual cues, can automatically generate highly memorable cues. We investigate the effectiveness of our approach via a human participant experiment by comparing it with manually generated cues.