Skip to content
conftrace_
2024 ICML ICML 2024

Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

❓ The Questioner

Authors

Yanda Chen, Ruiqi Zhong, Narutatsu Ri, Chen Zhao, He He, Jacob Steinhardt, Zhou Yu, Kathleen McKeown

Topics

Artificial Intelligence > Core AI > Human-AI Interaction Artificial Intelligence > Core AI > Interpretability Artificial Intelligence > Core AI > Large Language Models

Keywords

reward modeling natural language explanation large language model counterfactual simulatability generality precision
Download PDF