Papers by Quanwei Tang
Don’t Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing question answering (QA) datasets for long audio meetings suffer from acoustic information loss and poor long-term dependency capture. |
| Approach: | They propose a question answering dataset that captures three core dimensions of long-form audio meeting content. |
| Outcome: | The proposed model captures three core dimensions of long-form audio meeting content: complex semantics, multi-speaker interactions, and quite long timestamps. |
A Comprehensive Graph Framework for Question Answering with Mode-Seeking Preference Alignment (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies struggle with achieving global understanding of large language models . GraphMPA is a graph-based framework with mode-seeking preference alignment . |
| Approach: | They propose a graph-based framework with mode-seeking preference alignment to improve model outputs. |
| Outcome: | The proposed framework constructs a hierarchical document graph mimicking human cognitive processes for information understanding and synthesis. |