Measuring Understanding

Welcome to this year’s 2nd TRR Conference on “Measuring Understanding”.

Current XAI research is centring around solutions of how to achieve understanding. The topics include different methods and tools to assess and measure understanding in the context of (a) dyadic everyday explanations (b) the context of interpretability or explainability of AI systems, or (c) of institutional environments. Specifically, the focus of the conference is on the methodological challenge of how to measure and operationalise understanding in diverse explanatory settings including human-human interaction and human-machine interaction. Additionally, what are the implications of these measurements for XAI. Researchers from all around Europe are coming together to discuss recent challenges and topics how to measure understanding.

Re­sea­rch Tracks & Un­der­stan­ding Work­shop

Parallel Research Track 1 - Monday

15:45 - 17:15

CA and Ethnomethodology

Evaluating XAI via User Studies

AI for Education and Training

Chair:
Josephine B. Fisher

Room: L2.202

Chair:
Maximilian Muschalik

Room: L2.201

Chair:
Heike Buhl

Room: L1.201

What 'Counts' as Explanation in Social Interaction

Speaker:
Saul Albert

Evaluating Concept- and Relation-based Explanations for Image Classification

Speaker:
Bettina Finzel

From Machine Learning to Machine Teaching: How Human Can Learn form Explainable Artifical Intelligence

Speaker:
Dingrong Guo

Understanding Beyond Measurement

Speaker:
Nils Klowait

Evaluating a Multi-Modal Design for an Informative Take-Over Request in a Drone-Controller Setting

Speaker:
Emilia Ellsiepen

AR-mediated Explainability for Teaching and Cooperation

Speaker:
Anna Belardinelli

Understanding Robots in Public: The Influence of Other Humans' Presence on Human-Robot Interaction

Speaker:
Andrei Korbut

Understanding Path Planning Explanations

Speaker:
Amar Halilovic

Collaboration with AI Technologies: AI-Developed Curricula in Language Education

Speaker:
Dilsah Kalay

A, B, C, It's Easy as 1, 2, 3 - Inviting Linguistic Complexity to the Process of Operationalizing Understanding

Speaker:
Annedore Wilmes

What's happening right now? Passenger Understanding of Highly Automated Shuttle's Minimal Risk Maneuvers by Internal Human-Machine Interfaces

Speaker:
Thorben Brandt

 

Understanding Workshop - Tuesday

11:00 - 12:30

Chair:
Vivien Lohmer

Room: L2.202

Measuring the Progress of Understanding of the Explainee via Substantive Contributions in Explanatory Dialogues

Speaker:
Josephine B. Fisher

Approaches of Assessing Understanding Using Video-Recall Data

Speaker:
Stefan Lazarov
Michael Schaffer
Erick K. Ronoh

Measuring Intra-Individual Differences in Signals of Understanding

Speaker:
Jonas Paletschek
David Johnson
Hanna Drimalla

Parallel Research Track 2 - Tuesday

13:45 - 15:15

Developing Instruments and Models for Measuring Understanding Classification of Understanding and Human Oversight Psychological and Cognitive Science View on XAI

Chair:
tba

Room: L2.202

Chair:
tba

Room: L2.201

Chair:
Heike Buhl

Room: L1.201

Unraveling the Relationship Between Explanation as a Process and Understanding. Using the Block Model as Holistic Framework for Understanding Explainable AI

Speaker:
Carsten Schulte

Towards a BFO-based Ontology of Understanding Explanations

Speaker:
Meisam Booshehri

Mental Model Disparity and its Effect on User Understanding and Satisfaction in XAI

Speaker:
Jaroslaw Kornowicz

Conceptualization of Subjective Understanding towards Scale Development

Speaker:
Theresa Waclawek
Angela Fiedler

Beyond Understanding. Towards a Comprehensive Measure of Human Oversight in AI

Speaker:
Nikolai Ebinger

A Machine Learning Approach to the Prediction of Individual Differences in Psychological Reactivities

Speaker:
Ole Hätscher

A Communication Architecture for Measuring Understanding

Speaker:
Charles Wan

Understanding as an Interactive Precondition and a Problem: Securing of Understanding in Calls to the Ministry for State Security of the GDR

Speaker:
Olga Galanova

Do Humans and CNN Better Understand the Visual Explanations Generated by other Humans or XAI Algorithms?

Speaker:
Romy Müller

Meta AI Literacy Scale: Development and Testing of an AI Literacy Questionnaire Based on Well-Founded Competency Models and Psychological Change and Meta-Competencies

Speaker:
Martin Koch

Unfooling SHAP and SAGE: Knockoff Imputation for Shapley Values

Speaker:
Kristin Blesch

Shedding Light: A Survey of Concept-Based Explainable AI

Speaker:
Eleonora Poeta

Parallel Research Track 3 - Tuesday

15:45 - 16:30

Evaluation of Explanations On the Interpretation of XAI Results

Chair:
tba

Room: L2.202

Chair:
tba

Room: L2.201

Modeling the Quality of Dialogical Explanations

Speaker:
Henning Wachsmuth

Pitfalls of Interpreting the Shapley Value in Explainable AI

Speaker:
Patrick Kolpaczki

Compare-xAI: Toward Unifying Functional Testing Methods for Post-hoc XAI Algorithms into a Multi-dimensional Benchmark

Speaker:
Karim Belaid

On the Confounding Roles of Explanation Faithfulness and Intuitivity in Measuring Understanding

Speaker:
Tobias Leemann

General questions go to conference@trr318.uni-paderborn.de,

media enquiries to communication@trr318.uni-paderborn.de.