Poster
in
Workshop: Challenges in Deployable Generative AI
Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions
Skyler Wu · Eric Shen · Charumathi Badrinath · Jiaqi Ma · Himabindu Lakkaraju
Keywords: [ robustness ] [ Machine Learning ] [ ICML ] [ Gradient-Based Feature Attribution ] [ Saliency Maps ] [ Chain of Thought Prompting ] [ Interpretability ] [ large language models ]