English

Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs

Computation and Language 2024-09-24 v1 Artificial Intelligence

Abstract

This paper introduces a novel task to assess the faithfulness of large language models (LLMs) using local perturbations and self-explanations. Many LLMs often require additional context to answer certain questions correctly. For this purpose, we propose a new efficient alternative explainability technique, inspired by the commonly used leave-one-out approach. Using this approach, we identify the sufficient and necessary parts for the LLM to generate correct answers, serving as explanations. We propose a metric for assessing faithfulness that compares these crucial parts with the self-explanations of the model. Using the Natural Questions dataset, we validate our approach, demonstrating its effectiveness in explaining model decisions and assessing faithfulness.

Keywords

Cite

@article{arxiv.2409.13764,
  title  = {Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs},
  author = {Christos Fragkathoulas and Odysseas S. Chlapanis},
  journal= {arXiv preprint arXiv:2409.13764},
  year   = {2024}
}