Papers by Yonghe Lu
D2-RAG: Dual-Decision Retrieval-Augmented Generation via Multi-Dimensional Uncertainty and Utility-Aware Decoding (2026.findings-acl)
Copied to clipboard
Jinshuo Zhang, Xiaoding Zhou, Weiyu Zhang, Guoqiang Chen, Ying Lian, Xiaoyang Meng, Yonghe Chen, Hongjiao Guan, Jiasheng Si, Wenpeng Lu
| Challenge: | Retrieval-Augmented Generation (RAG) mitigates hallucinations in large language models by incorporating external knowledge. |
| Approach: | They propose a dual-decision retrieval-augmented generation that integrates multi-dimensional uncertainty estimation to decide whether to retrieve and employs adaptive contrastive decoding to handle retrieved contexts of varying quality. |
| Outcome: | The proposed model outperforms baselines on four medical question-answering datasets while suppressing interference from noisy contexts. |
FNSCC: Fuzzy Neighborhood-Aware Self-Supervised Contrastive Clustering for Short Text (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Short texts pose significant challenges for clustering due to semantic sparsity, limited context and fuzzy category boundaries. |
| Approach: | proposed framework incorporates neighborhood information at instance and cluster levels . a cluster-level framework introduces fuzzy neighborhood-aware weighting . |
| Outcome: | The proposed framework outperforms state-of-the-art models on short texts . it excludes neighbors from negative sample set to enhance inter-cluster separability . |
MAST: A Multi-View Alignment Strategy for Optimal Transport-Based Contrastive Clustering of Short Text (2026.findings-acl)
Copied to clipboard
| Challenge: | Short text clustering has gained significant prominence due to its ubiquity in real-world applications. |
| Approach: | They propose a multi-view alignment strategy with transport-based clustering that integrates structural views to capture multi-granularity semantic features. |
| Outcome: | Experiments show that MAST outperforms state-of-the-art methods on benchmark datasets. |