Natural Language Explanation
Natural language explanation (NLE) research focuses on generating human-understandable explanations for AI model decisions, aiming to improve transparency, trust, and user understanding. Current efforts concentrate on developing methods to generate accurate, consistent, and faithful explanations using large language models (LLMs), often augmented with knowledge graphs or retrieval mechanisms, and evaluating these explanations using both automatic metrics and human assessments. This field is significant for enhancing the trustworthiness and usability of AI systems across diverse applications, from medicine and law to education and robotics, by bridging the gap between complex model outputs and human comprehension.
Papers
RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model
Jianhao Yuan, Shuyang Sun, Daniel Omeiza, Bo Zhao, Paul Newman, Lars Kunze, Matthew Gadd
Inference to the Best Explanation in Large Language Models
Dhairya Dalal, Marco Valentino, André Freitas, Paul Buitelaar
Using Natural Language Explanations to Improve Robustness of In-context Learning
Xuanli He, Yuxiang Wu, Oana-Maria Camburu, Pasquale Minervini, Pontus Stenetorp
Leveraging Multiple Teachers for Test-Time Adaptation of Language-Guided Classifiers
Kangda Wei, Sayan Ghosh, Rakesh R. Menon, Shashank Srivastava