5 papers
What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Generation
Qing Wang, Jacob Devasier, Chengkai Li
We present the first systematic study of masked diffusion language models (MDLMs) for graph-to-text generation. We analyze MDLM generation trajectories -- the order in which tokens…
Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style
Yuepei Li, Kang Zhou, Qiao Qiao +3
Retrieval-augmented generation (RAG) improves Large Language Models (LLMs) by incorporating external information into the response generation process. However, how context-faithful…
Bridge: A Unified Framework to Knowledge Graph Completion via Language Models and Knowledge Representation
Qiao Qiao, Yuepei Li, Qing Wang +2
Knowledge graph completion (KGC) is a task of inferring missing triples based on existing Knowledge Graphs (KGs). Both structural and semantic information are vital for successful…
Towards a More Generalized Approach in Open Relation Extraction
Qing Wang, Yuepei Li, Qiao Qiao +2
Open Relation Extraction (OpenRE) seeks to identify and extract novel relational facts between named entities from unlabeled data without pre-defined relation schemas. Traditional…
Re-Examine Distantly Supervised NER: A New Benchmark and a Simple Approach
Yuepei Li, Kang Zhou, Qiao Qiao +2
Distantly-Supervised Named Entity Recognition (DS-NER) uses knowledge bases or dictionaries for annotations, reducing manual efforts but rely on large human labeled validation set.…