Ziems et al. (2022) conducted experiments on seven different Large Language Models using a moral integrity dataset comprising 20,000 samples and instructions to investigate whether GPT-3.5's behavior regarding moral questions is unique.

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 (2)

• Large Language Models concept
• GPT 3.5 concept