Jihyun Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jihyun Lee has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Gary Geunbae Lee
Graduate School of Artificial Intelligence POSTECH Republic of Korea
7 shared publications Yejin Jeon
Graduate School of Artificial Intelligence POSTECH Republic of Korea
5 shared publicationsSeungyeon Seo
Graduate School of Artificial Intelligence POSTECH Republic of Korea
3 shared publications- Hyounghun Kim
Graduate School of Artificial Intelligence POSTECH Republic of Korea
2 shared publications Youngjae Kim
Graduate School of Artificial Intelligence POSTECH Republic of Korea
2 shared publicationsSan Kim
Graduate School of Artificial Intelligence Department of Computer Science and Engineering POSTECH ♢ POSTECH
1 shared publication
Latest Publications
- Open Access
PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona
Task-Oriented Dialogue (TOD) systems are designed to fulfill user requests through natural language interactions, yet existing systems often produce generic, monotonic responses that lack individuality and fail to adapt to users' personal attributes. To address this, we introduce PicPersona-TOD, a novel dataset that incorporates user images as part of the persona, enabling personalized responses tailored to user-specific factors such as age or emotional context. This is facilitated by first impressions, dialogue policy-guided prompting, and the use of external knowledge to reduce hallucinations. Human evaluations confirm that our dataset enhances user experience, with personalized responses contributing to a more engaging interaction. Additionally, we introduce a new NLG model, Pictor, which not only personalizes responses, but also demonstrates robust performance across unseen domains https://github.com/JihyunLee1/PicPersona.
Open AccessPicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona
Task-Oriented Dialogue (TOD) systems are designed to fulfill user requests through natural language interactions, yet existing systems often produce generic, monotonic responses that lack individuality and fail to adapt to users' personal attributes. To address this, we introduce PicPersona-TOD, a novel dataset that incorporates user images as part of the persona, enabling personalized responses tailored to user-specific factors such as age or emotional context. This is facilitated by first impressions, dialogue policy-guided prompting, and the use of external knowledge to reduce hallucinations. Human evaluations confirm that our dataset enhances user experience, with personalized responses contributing to a more engaging interaction. Additionally, we introduce a new NLG model, Pictor, which not only personalizes responses, but also demonstrates robust performance across unseen domains https://github.com/JihyunLee1/PicPersona.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 12853-12885
PanicToCalm: A Proactive Counseling Agent for Panic Attacks
Jihyun Lee, Yejin Min, San Kim, Yejin Jeon, Sung Jun Yang, Hyounghun Kim, Gary Lee. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 12853-12885
Open AccessPanicToCalm: A Proactive Counseling Agent for Panic Attacks
Jihyun Lee, Yejin Min, San Kim, Yejin Jeon, Sung Jun Yang, Hyounghun Kim, Gary Lee. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 2799-2811
Progressive Facial Granularity Aggregation with Bilateral Attribute-based Enhancement for Face-to-Speech Synthesis
Yejin Jeon, Youngjae Kim, Jihyun Lee, Hyounghun Kim, Gary Lee. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 2799-2811
Open AccessProgressive Facial Granularity Aggregation with Bilateral Attribute-based Enhancement for Face-to-Speech Synthesis
Yejin Jeon, Youngjae Kim, Jihyun Lee, Hyounghun Kim, Gary Lee. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 638-650
Prompt-Guided Selective Masking Loss for Context-Aware Emotive Text-to-Speech
Yejin Jeon, Youngjae Kim, Jihyun Lee, Gary Lee. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 638-650
Open AccessPrompt-Guided Selective Masking Loss for Context-Aware Emotive Text-to-Speech
Yejin Jeon, Youngjae Kim, Jihyun Lee, Gary Lee. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7937-7958
PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona
Jihyun Lee, Yejin Jeon, Seungyeon Seo, Gary Lee. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7937-7958
Open AccessPicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona
Jihyun Lee, Yejin Jeon, Seungyeon Seo, Gary Lee. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.
- Open Access
Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT
Traditional dialogue state tracking approaches heavily rely on extensive training data and handcrafted features, limiting their scalability and adaptability to new domains. In this paper, we propose a novel method that leverages inference and in-context learning with ChatGPT for domain transfer in dialogue state tracking, without any parameter updates. By guiding ChatGPT's chain of thought, we enable it to retrieve relevant examples and generalize knowledge to accurately infer dialogue states, solely through inference. Experimental results on the MultiWOZ dataset demonstrate competitive performance and promising generalization across domains. Our parameter-free approach offers a scalable and adaptable solution, opening new research directions in domain transfer learning.
Open AccessInference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT
Traditional dialogue state tracking approaches heavily rely on extensive training data and handcrafted features, limiting their scalability and adaptability to new domains. In this paper, we propose a novel method that leverages inference and in-context learning with ChatGPT for domain transfer in dialogue state tracking, without any parameter updates. By guiding ChatGPT's chain of thought, we enable it to retrieve relevant examples and generalize knowledge to accurately infer dialogue states, solely through inference. Experimental results on the MultiWOZ dataset demonstrate competitive performance and promising generalization across domains. Our parameter-free approach offers a scalable and adaptable solution, opening new research directions in domain transfer learning.
- Open Access
DORIC : Domain Robust Fine-Tuning for Open Intent Clustering through Dependency Parsing
We present our work on Track 2 in the Dialog System Technology Challenges 11 (DSTC11). DSTC11-Track2 aims to provide a benchmark for zero-shot, cross-domain, intent-set induction. In the absence of in-domain training dataset, robust utterance representation that can be used across domains is necessary to induce users' intentions. To achieve this, we leveraged a multi-domain dialogue dataset to fine-tune the language model and proposed extracting Verb-Object pairs to remove the artifacts of unnecessary information. Furthermore, we devised the method that generates each cluster's name for the explainability of clustered results. Our approach achieved 3rd place in the precision score and showed superior accuracy and normalized mutual information (NMI) score than the baseline model on various domain datasets.
Open AccessDORIC : Domain Robust Fine-Tuning for Open Intent Clustering through Dependency Parsing
We present our work on Track 2 in the Dialog System Technology Challenges 11 (DSTC11). DSTC11-Track2 aims to provide a benchmark for zero-shot, cross-domain, intent-set induction. In the absence of in-domain training dataset, robust utterance representation that can be used across domains is necessary to induce users' intentions. To achieve this, we leveraged a multi-domain dialogue dataset to fine-tune the language model and proposed extracting Verb-Object pairs to remove the artifacts of unnecessary information. Furthermore, we devised the method that generates each cluster's name for the explainability of clustered results. Our approach achieved 3rd place in the precision score and showed superior accuracy and normalized mutual information (NMI) score than the baseline model on various domain datasets.