Explingo: Explaining AI Predictions using Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zytek, Alexandra, Pido, Sara, Alnegheimish, Sarah, Berti-Equille, Laure, Veeramachaneni, Kalyan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910731157372928
author Zytek, Alexandra
Pido, Sara
Alnegheimish, Sarah
Berti-Equille, Laure
Veeramachaneni, Kalyan
author_facet Zytek, Alexandra
Pido, Sara
Alnegheimish, Sarah
Berti-Equille, Laure
Veeramachaneni, Kalyan
contents Explanations of machine learning (ML) model predictions generated by Explainable AI (XAI) techniques such as SHAP are essential for people using ML outputs for decision-making. We explore the potential of Large Language Models (LLMs) to transform these explanations into human-readable, narrative formats that align with natural communication. We address two key research questions: (1) Can LLMs reliably transform traditional explanations into high-quality narratives? and (2) How can we effectively evaluate the quality of narrative explanations? To answer these questions, we introduce Explingo, which consists of two LLM-based subsystems, a Narrator and Grader. The Narrator takes in ML explanations and transforms them into natural-language descriptions. The Grader scores these narratives on a set of metrics including accuracy, completeness, fluency, and conciseness. Our experiments demonstrate that LLMs can generate high-quality narratives that achieve high scores across all metrics, particularly when guided by a small number of human-labeled and bootstrapped examples. We also identified areas that remain challenging, in particular for effectively scoring narratives in complex domains. The findings from this work have been integrated into an open-source tool that makes narrative explanations available for further applications.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05145
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Explingo: Explaining AI Predictions using Large Language Models
Zytek, Alexandra
Pido, Sara
Alnegheimish, Sarah
Berti-Equille, Laure
Veeramachaneni, Kalyan
Computation and Language
Artificial Intelligence
Machine Learning
Explanations of machine learning (ML) model predictions generated by Explainable AI (XAI) techniques such as SHAP are essential for people using ML outputs for decision-making. We explore the potential of Large Language Models (LLMs) to transform these explanations into human-readable, narrative formats that align with natural communication. We address two key research questions: (1) Can LLMs reliably transform traditional explanations into high-quality narratives? and (2) How can we effectively evaluate the quality of narrative explanations? To answer these questions, we introduce Explingo, which consists of two LLM-based subsystems, a Narrator and Grader. The Narrator takes in ML explanations and transforms them into natural-language descriptions. The Grader scores these narratives on a set of metrics including accuracy, completeness, fluency, and conciseness. Our experiments demonstrate that LLMs can generate high-quality narratives that achieve high scores across all metrics, particularly when guided by a small number of human-labeled and bootstrapped examples. We also identified areas that remain challenging, in particular for effectively scoring narratives in complex domains. The findings from this work have been integrated into an open-source tool that makes narrative explanations available for further applications.
title Explingo: Explaining AI Predictions using Large Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.05145