Scherrer et al. (2023) found that Large Language Models focus on generating fluent sentences while overlooking important words or concepts that contribute to stable decisions when examined in moral scenarios.

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