The DRO method, proposed by Shi et al. (2025), utilizes a direct retrieval-augmentation approach to estimate the distribution of document permutations from a selected model, enabling the joint learning of both the selection model and the generative Large Language Model.

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 (1)

• generative large language models concept