GPT 3.5 exhibits fragility in its safety and instruction-following capabilities, as paraphrased versions of an initial query can disrupt the model's performance.

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)

• GPT 3.5 concept