Papers by Hyun-Sik Won
Large Language Models are Students at Various Levels: Zero-shot Question Difficulty Estimation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advancements in educational platforms have emphasized the importance of personalized education. |
| Approach: | They propose a framework that utilizes large language models to represent students at various levels to estimate question difficulty with and without student question-solving records. |
| Outcome: | The proposed framework outperforms baseline models on the DBE-KT22 and ASSISTMents 2005–2006 benchmarks and shows a high correlation with the regressed IRT curve. |
End-to-End Multilingual Automatic Dubbing via Duration-based Translation with Large Language Models (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Automatic dubbing (AD) aims to replace the original speech with translated speech that maintains precise temporal alignment (isochrony). |
| Approach: | They propose an end-to-end automatic dubbing framework that leverages large language models to integrate translation and timing control seamlessly. |
| Outcome: | The proposed framework achieves up to 24% relative gains on English, Spanish, and Korean language pairs while maintaining competitive translation quality measured by COMET scores. |