Foundations of explanations as model reconciliation

Sarath Sreedharan, Tathagata Chakraborti, Subbarao Kambhampati

Research output: Contribution to journalArticlepeer-review

Abstract

Past work on plan explanations primarily involved the AI system explaining the correctness of its plan and the rationale for its decision in terms of its own model. Such soliloquy is wholly inadequate in most realistic scenarios where users have domain and task models that differ from that used by the AI system. We posit that the explanations are best studied in light of these differing models. In particular, we show how explanation can be seen as a “model reconciliation problem” (MRP), where the AI system in effect suggests changes to the user's mental model so as to make its plan be optimal with respect to that changed user model. We will study the properties of such explanations, present algorithms for automatically computing them, discuss relevant extensions to the basic framework, and evaluate the performance of the proposed algorithms both empirically and through controlled user studies.

Original languageEnglish (US)
Article number103558
JournalArtificial Intelligence
Volume301
DOIs
StatePublished - Dec 2021
Externally publishedYes

Keywords

  • Automated planning
  • Explainable AI
  • Mental models

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Foundations of explanations as model reconciliation'. Together they form a unique fingerprint.

Cite this