Chirag Agarwal

A new method enhances the safety of language models against harmful prompts.

Examining how robust machine learning models impact explanation effectiveness.

Examining the challenges of self-explanations in large language models.

Examining the effectiveness of reasoning in large language models.

This article discusses protecting our personal data from language models.

Exploring how fine-tuning affects reasoning in language models.

LVLMs struggle with recognizing reality, risking serious consequences.