# Responsibility: An Example-based Explainable AI approach via Training Process Inspection

Source: [Responsibility: An Example-based Explainable AI approach via Training Process Inspection](<https://www.sota2.com/research/paper/68fa6d6a1e209131cea39aa4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:17:30.291Z

Authors: Faraz Khadivpour, Arghasree Banerjee, Matthew Guzdial

Published: 2022-09-07T19:30:01.000Z

## Abstract

Explainable Artificial Intelligence (XAI) methods are intended to help human users better understand the decision making of an AI agent. However, many modern XAI approaches are unintuitive to end users, particularly those without prior AI or ML knowledge. In this paper, we present a novel XAI approach we call Responsibility that identifies the most responsible training example for a particular decision. This example can then be shown as an explanation: "this is what I (the AI) learned that led me to do that". We present experimental results across a number of domains along with the results of an Amazon Mechanical Turk user study, comparing responsibility and existing XAI methods on an image classification task. Our results demonstrate that responsibility can help improve accuracy for both human end users and secondary ML models.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2209.03433>)

[PDF](<https://arxiv.org/pdf/2209.03433.pdf>)