Publications

Conference Papers

Evaluation of Multi-Agent LLMs in Multidisciplinary Team Decision-Making for Challenging Cancer Cases

Published in Machine Learning for Healthcare (MLHC), 2025

This paper evaluates the effectiveness of multi-agent large language models in collaborative medical decision-making for complex cancer cases, investigating how AI agents can simulate multidisciplinary team dynamics.

Recommended citation: Jaesik Kim*, Byounghan Lee*, Kyung-Ah Sohn, Dokyoon Kim, Young Chan Lee. (2025). "Evaluation of Multi-Agent LLMs in Multidisciplinary Team Decision-Making for Challenging Cancer Cases." Machine Learning for Healthcare (MLHC).

Counter Narrative Generation through Knowledge-Injected Prompt Learning

Published in Korea Software Congress (KSC2024), 2024

A novel approach to generate effective counter-narratives against hate speech using knowledge-injected prompt learning techniques.

Recommended citation: Hyeonwoo Jung, Byounghan Lee, Kyung-Ah Sohn. (2024). "Counter Narrative Generation through Knowledge-Injected Prompt Learning." Korea Software Congress (KSC2024), Yeosu, South Korea.

Efficient Privacy-Preserving Chatbot Learning through Prefix-Learning Based Federated Learning

Published in Conference on Information Security and Cryptography-Winter (CISC-W 2023), 2023

A novel federated learning approach for privacy-preserving chatbot training using prefix-learning techniques to reduce communication costs while maintaining performance.

Recommended citation: Kyungju Choi, Byounghan Lee, Kyung-Ah Sohn. (2023). "Efficient Privacy-Preserving Chatbot Learning through Prefix-Learning Based Federated Learning." Conference on Information Security and Cryptography-Winter (CISC-W 2023), Seoul, South Korea.

Korean Hate Speech Detection Using Hate-Rationale Word Prediction

Published in Korea Software Congress (KSC2023), 2023

A novel approach for Korean hate speech detection that improves performance by predicting hate-rationale words that contribute to hateful expressions.

Recommended citation: Yunseo Choi, Byounghan Lee, Kyung-Ah Sohn. (2023). "Korean Hate Speech Detection Using Hate-Rationale Word Prediction." Korea Software Congress (KSC2023), Busan, South Korea.

Improving Unsupervised Out-of-domain Detection through Pseudo Labeling and Learning

Published in Findings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2023

A novel two-stage framework for unsupervised out-of-domain detection that significantly outperforms baseline models through strategic pseudo labeling approaches.

Recommended citation: Byounghan Lee, Jaesik Kim, Junekyu Park, Kyung-Ah Sohn. (2023). "Improving Unsupervised Out-of-domain Detection through Pseudo Labeling and Learning." Findings of the Association for Computational Linguistics: EACL 2023, pages 1031–1041.
Download Paper

Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection

Published in International Conference on Computational Linguistics (COLING), 2022

An explainable AI approach for hate speech detection using masked rationale prediction to improve both bias mitigation and model interpretability.

Recommended citation: Jiyun Kim, Byounghan Lee, Kyung-Ah Sohn. (2022). "Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection." Proceedings of the 29th International Conference on Computational Linguistics (COLING), pages 6644–6655.
Download Paper

Disaster Detection Using Text Anomaly Detection in SNS

Published in Korea Next Generation Computing Conference (KINGPC), 2022

A text anomaly detection approach for identifying disaster-related events from social media posts, enabling early warning and rapid response systems.

Recommended citation: Byounghan Lee, Kyung-Ah Sohn. (2022). "Disaster Detection Using Text Anomaly Detection in SNS." Korea Next Generation Computing Conference (KINGPC), South Korea.