Papers by Yonghe Lu

3 papers
D2-RAG: Dual-Decision Retrieval-Augmented Generation via Multi-Dimensional Uncertainty and Utility-Aware Decoding (2026.findings-acl)

Copied to clipboard

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations