Prasanna Sattigeri

A new method enhances probability accuracy in language models without extra data.

MExGen framework improves explanations for generative language models, enhancing user trust.

Research explores ways to improve trust in LLM outputs through factuality and sourcing.

A new model detects social bias in text using synthetic data.

Addressing security risks in generative AI through red and blue teaming.

Granite Guardian safeguards AI conversations from harmful content effectively.