Explainable NLP

We propose a scientific analogical reasoning benchmark with structure abduction, SCAR, and show that large language models make reasonable scientific analogies after structure abduction.

Generate explanations for why a statement is wrong by prompting LLMs with the correct version of it.

For humans, intuitive inferences are made every now and then. However, it would require reasons for humans to convince others and justify themselves of their inferences or decisions. How can machines better convince humans of their predictions? The key may lie in being right for the right and faithful reasons.

We benchmark knowledge-intensive analogical reasoning with human-annotated explanations.

Interpretable fact verification with phrasal decomposition and logic regularization.

A novel approach for joint answer prediction and proof generation.