Papers by Soo Yong Kim
Jamendo-MT-QA: A Benchmark for Multi-Track Comparative Music Question Answering (2026.findings-acl)
Copied to clipboard
Junyoung Koh, Jaeyun Lee, Soo Yong Kim, Gyu Hyeong Choi, Jung In Koh, Jordan Phillips, Yeonjin Lee, Min Song
| Challenge: | Existing benchmarks for music question answering do not systematically evaluate reasoning across tracks. |
| Approach: | They propose a dataset and benchmark for multi-track comparative question answering . they construct 36,519 comparative QA items over 12,173 track pairs . |
| Outcome: | The proposed dataset and benchmark for multi-track comparative question answering is based on the Jamendo-QA dataset. |
‘Hello, World!’: Making GNNs Talk with LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | graph neural networks have shown remarkable performance across diverse graph-related tasks, but their high-dimensional hidden representations render them black boxes. |
| Approach: | They propose a graph-based neural network with hidden representations in the form of human-readable text. |
| Outcome: | The proposed GNN outperforms existing LLM-based baseline methods on node classification and link prediction. |