Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations

1 code implementation • 6 Oct 2023 • Deren Lei, Yaxi Li, Mengya Hu, Mingyu Wang, Vincent Yun, Emily Ching, Eslam Kamal

Our framework uses Chain of Natural Language Inference (CoNLI) for hallucination detection and hallucination reduction via post-editing.

Hallucination Language Modelling +3