Towards understanding and mitigating the hallucinations in NLP and Speech

CODS-COMAD '24: Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)

Dayananda Sagar University

Authors: Ashish Mittal Rudra Murthy Vishwajeet Kumar Riyaz Bhat

Abstract

This tutorial covers the hallucination phenomenon observed in generative AI models like autoregressive models and sequence-to-sequence models. The tutorial also provides a bird's eye-view of the approaches to mitigate hallcuinations.