AI Paper Atlas

Research map / Large language models / AI and society

Towards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations

Yao Rong, Tobias Leemann, Thai-trang Nguyen, Lisa Fiedler, Peizhu Qian, Vaibhav Vasant Unhelkar, Tina Seidel, Gjergji Kasneci, Enkelejda Kasneci

TPAMI 2023 · Large language models › AI and society · approach: Human-centered trust and agency · 393 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add explanations versus no explanationsuser trust in AI · XAI user studiesuser trustMixed
add explanations in autonomous drivinguser trust · autonomous driving, simulation vs real footagetrustMixed
add SHAP explanations to white-box models versus black-box without explanationsobjective understanding · simulatability taskssimulation performanceHurt
add anchors or prototype explanationsobjective understanding · user studyobjective understandingNo clear effect
add highlighted important words as explanations in text classificationuser trust and satisfaction · text classificationtrust and satisfactionHurt
add feature importance scores or counterfactual explanationsperceived fairness · decision explanationperceived fairnessImproved
add explanations for novices versus expertshuman-AI collaboration performance · human-AI decision makinghuman performanceMixed
add model explanations for detecting incorrect predictionsfailure detection · user studyincorrect prediction identificationHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy