# Explanation as Question Answering based on a Task Model of the Agent's Design

Source: [Explanation as Question Answering based on a Task Model of the Agent's Design](<https://www.sota2.com/research/paper/68fa6cc61e209131cea35e51>)

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

Data updated: 2025-10-28T13:56:53.905Z

Authors: Ashok Goel, Harshvardhan Sikka, Vrinda Nandan, Jeonghyun Lee, Matt Lisle, Spencer Rugaber

Published: 2022-06-08T08:52:47.000Z

## Abstract

We describe a stance towards the generation of explanations in AI agents that is both human-centered and design-based. We collect questions about the working of an AI agent through participatory design by focus groups. We capture an agent's design through a Task-Method-Knowledge model that explicitly specifies the agent's tasks and goals, as well as the mechanisms, knowledge and vocabulary it uses for accomplishing the tasks. We illustrate our approach through the generation of explanations in Skillsync, an AI agent that links companies and colleges for worker upskilling and reskilling. In particular, we embed a question-answering agent called AskJill in Skillsync, where AskJill contains a TMK model of Skillsync's design. AskJill presently answers human-generated questions about Skillsync's tasks and vocabulary, and thereby helps explain how it produces its recommendations.

## 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/2206.05030>)

[PDF](<https://arxiv.org/pdf/2206.05030.pdf>)