AI RESEARCH
A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification
arXiv CS.CL
•
ArXi:2410.03296v4 Announce Type: replace Instruction-tuned LLMs are able to provide \textit{an} explanation about their output to users by generating self-explanations, without requiring the application of complex interpretability techniques. In this paper, we analyse whether this ability results in a \textit{good} explanation. We evaluate self-explanations in the form of input rationales with respect to their plausibility to humans. We study three text classification tasks: sentiment classification, forced labour detection and claim verification.