GLens, proposed by Zheng et al. (2024a), uses a Thompson sampling strategy to measure alignment between Knowledge Graphs and LLMs to identify knowledge blind spots, and employs a graph-guided question generator to convert Knowledge Graphs to text while using a sampling strategy on the parameterized KG structure to accelerate traversal.

Authors

• Person: Not available Organization: arXiv
  Large Language Models Meet Knowledge Graphs for Question ...

Sources

• Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv via serper

Referenced by nodes (2)

• Large Language Models concept
• knowledge graphs concept