Papers by Dehai Min

3 papers
UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers (2025.naacl-long)

Copied to clipboard

Challenge: Existing information retrieval models assume a homogeneous structure for knowledge sources and user queries, limiting their applicability in real-world settings.
Approach: They propose a unified instruction-aware heterogeneous knowledge retriever that builds a heterogenous retrieval space for heterogenized knowledge and follows diverse user instructions to retrieve knowledge in specified types.
Outcome: The proposed framework outperforms state-of-the-art methods on CompMix-IR . it achieves 6.36% relative improvements and 54.23% relative improvements .
Three Stream Based Multi-level Event Contrastive Learning for Text-Video Event Extraction (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for event extraction ignore motion representations in videos and are misguided by background noise.
Approach: They propose a text-video based multimodal event extraction framework that integrates video appearance features and motion representations with video appearance.
Outcome: The proposed framework outperforms the state-of-the-art methods in the event extraction field.
QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for reducing LLM hallucinations rely on model-internal signals . Existing approaches rely only on model internal signals, resulting in unreliability .
Approach: They propose a method that shifts from subjective confidence to objective statistics . they leverage Infini-gram for millisecond-latency queries over 4 trillion tokens .
Outcome: The proposed method reduces hallucinations in large language models by reducing uncertainty in the model.

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