The Deep Ensemble of LLMs approach uses external knowledge as reward functions during the ensembling process to promote logical consistency and meaningful connections within the generated text.

Authors

• Person: Not available Organization: arXiv
  Building Trustworthy NeuroSymbolic AI Systems - arXiv

Sources

• Building Trustworthy NeuroSymbolic AI Systems - arXiv arxiv.org arXiv via serper

Referenced by nodes (1)

• Large Language Models concept