Explainable Adaptive Assistants Deborah L. McGuinness, Tetherless World Constellation, RPI Alyssa Glass, Stanford University Michael Wolverton, SRI International Paulo Pinheiro da Silva, University of Texas at El Paso Cynthia Chang, Tetherless World Constellation, RPI Li Ding, Tetherless World Constellation, RPI Designed to  Extract an explanation-relevant snapshot of execution state, including learning provenance  Communicate that information to the Explainer System utilizes introspective predicates to build a justification of current task(s), then outputs the justification structure via an RDBMS  Database schema designed for easy, scalable storage and retrieval of relevant execution and provenance information  Designed to be reusable for other types of reasoning about execution and action Architecture Motivation Usable adaptive assistants need to be able to explain their recommendations if users are expected to trust them. Our work on ICEE -- the Integrated Cognitive Explanation Environment -- provides an extensible infrastructure for supporting explanations. We aim to improve trust in learning- enabled agents by providing transparency concerning:  Provenance  Information manipulation  Task processing  Learning The ICEE explainer includes:  Descriptions of question types and explanation strategies  Architecture for generating interoperable, machine interpretable, sharable justifications of answers containing enough information to generate explanations  Components capable of obtaining justification information from SPARK (a BDI agent architecture)  History of execution states as justifications User Studies 1. Interviewed 13 adaptive agent users, focusing on trust, failures, surprises, and other sources of confusion. Identified themes on trusting adaptive agents, including:  Learning can make users feel ignored  Users want to ask questions when they perceive failures  Granularity of feedback is vitally important  Users need transparency and access to knowledge provenance  Users require explainable verification to build trust 2. Study planned for 1Q09 focusing on conflicts and trust Dialogue Given a PML justification of SPARK’s execution, ICEE provides a dialogue interface to explaining actions. Users can start a dialogue with any of several question types, for example: “Why are you doing ?” ICEE contains several explanation strategies for each question type and, based on context and a user model, chooses one strategy, for example: Strategy: Reveal task hierarchy “I am trying to do and is one subgoal in the process.” ICEE then parses the execution justification to present the portions relevant to the query and the explanation strategy. Strategies for explaining learned and modified procedures focus on provenance information and the learning method used. ICEE also suggests follow-up queries, enabling back- and-forth dialogue between agent and the user. SPARK Wrapper and Database CALO GUI PML Generator Task Manager (TM) TM WrapperTM Explainer Explanation Dispatcher Task database Glass, A., McGuinness, D.L., and Wolverton, M. “Toward Establishing Trust in Adaptive Agents.” IUI 2008 Alyssa Glass, Deborah L. McGuinness, Paulo Pinheiro da Silva, and Michael Wolverton. Trustable Task Processing Systems. In Roth-Berghofer, T., and Richter, M.M., editors, KI Journal, Special Issue on Explanation, Kunstliche Intelligenz, Jiao TaoJiao Tao,Li Ding,Jie Bao,Deborah L. McGuinness. Characterizing and Detecting Integrity Issues in OWL Instance Data, In OWLED 2008 EU, 2008Li DingJie BaoDeborah L. McGuinnessCharacterizing and Detecting Integrity Issues in OWL Instance Data Paulo Pinheiro da SilvaPaulo Pinheiro da Silva,Deborah McGuinness,Li Ding,Nicholas Del Rio. Inference Web in Action: Lightweight Use of Proof Markup Language, In ISWC'08, October,2008.Deborah McGuinnessLi DingNicholas Del RioInference Web in Action: Lightweight Use of Proof Markup Language Paulo Pinheiro da SilvaPaulo Pinheiro da Silva,Nicholas Del Rio,Deborah McGuinness,Li Ding,Cynthia Chang,Geoff Sutcliffe. User Interfaces for Portable Proofs, In UITP'08), August,2008Nicholas Del RioDeborah McGuinnessLi DingCynthia ChangGeoff SutcliffeUser Interfaces for Portable Proofs UseAsk UnderstandUpdate PML : Provenance, Justification, and Trust Interlingua Inference Web Toolkit : Suite of tools for generating, browsing, searching, validating, and summarizing explanations ICEE : Explanation framework for explaining cognitive agents, with focus on task processing and learning Explanation Foundation Current Focus  Added strategies focused on conflicts  Underlying infrastructure updates for combinations of justifications  Explanation generation and abstraction strategies based on improvement criteria including step minimization.  Identifying integrity issues that require explanation