Papers by Tan Yongmei
Enhancing Knowledge Selection via Multi-level Document Semantic Graph (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods view knowledge selection as a sentence matching or classification. Existing techniques can’t capture the semantic relationships within complex documents. |
| Approach: | They propose a method that can construct multi-level document semantic graph from the grounding document and store semantic relationships within the documents effectively. |
| Outcome: | The proposed method can store semantic relationships within documents effectively and efficiently and achieve state-of-the-art results on public datasets. |
Frozen LLMs are Native Decoders for High-Norm Semantic Vectors (2026.acl-long)
Copied to clipboard
| Challenge: | Existing compression methods selectively prune tokens based on information-theoretic metrics, resulting in interpretability but risking the loss of fine-grained information. |
| Approach: | They propose a landmark-based compression framework for long contexts that captures global dependencies over landmark tokens. |
| Outcome: | The proposed framework outperforms soft compression baselines on four QA benchmarks. |