Saved in:
Bibliographic Details
Main Authors: Kalo, Jan-Christoph, Polat, Fina, Guha, Shubha, Groth, Paul
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.17761
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916860654518272
author Kalo, Jan-Christoph
Polat, Fina
Guha, Shubha
Groth, Paul
author_facet Kalo, Jan-Christoph
Polat, Fina
Guha, Shubha
Groth, Paul
contents Modern AI systems are complex workflows containing multiple components and data sources. Data provenance provides the ability to interrogate and potentially explain the outputs of these systems. However, provenance is often too detailed and not contextualized for the user trying to understand the AI system. In this work, we present our vision for an interactive agent that works together with the user to co-construct an explanation that is simultaneously useful to the user as well as grounded in data provenance. To illustrate this vision, we present: 1) an initial prototype of such an agent; and 2) a scalable evaluation framework based on user simulations and a large language model as a judge approach.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17761
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Co-constructing Explanations for AI Systems using Provenance
Kalo, Jan-Christoph
Polat, Fina
Guha, Shubha
Groth, Paul
Human-Computer Interaction
Modern AI systems are complex workflows containing multiple components and data sources. Data provenance provides the ability to interrogate and potentially explain the outputs of these systems. However, provenance is often too detailed and not contextualized for the user trying to understand the AI system. In this work, we present our vision for an interactive agent that works together with the user to co-construct an explanation that is simultaneously useful to the user as well as grounded in data provenance. To illustrate this vision, we present: 1) an initial prototype of such an agent; and 2) a scalable evaluation framework based on user simulations and a large language model as a judge approach.
title Co-constructing Explanations for AI Systems using Provenance
topic Human-Computer Interaction
url https://arxiv.org/abs/2507.17761