Interpretability

Conversational XAI and Explanation Dialogues
My main research interest is human-centric explainability, i.e., making language models more interpretable by building applications …
PDF Cite
Towards Modeling and Evaluating Instructional Explanations in Teacher-Student Dialogues
For dialogues in which teachers explain difficult concepts to students, didactics research often debates which teaching strategies lead …
Cite DOI
Democratizing Advanced Attribution Analyses of Generative Language Models with the Inseq Toolkit
Inseq 1 is a recent toolkit providing an intuitive and optimized interface to conduct feature attribution analyses of generative …
PDF Cite
QoEXplainer: Mediating Explainable Quality of Experience Models with Large Language Models
In this paper, we present QoEXplainer, a QoE dashboard for supporting humans in understanding the internals of an explainable, …
Cite DOI
The Role of Explainability in Collaborative Human-AI Disinformation Detection
Manual verification has become very challenging based on the increasing volume of information shared online and the role of generative …
PDF Cite DOI
Inseq: An Interpretability Toolkit for Sequence Generation Models
Past work in natural language processing interpretability focused mainly on popular classification tasks while largely overlooking …
PDF Cite Code
Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods
Saliency maps can explain a neural model’s predictions by identifying important input features. They are difficult to interpret …
PDF Cite Code
XAINES: Explaining AI with Narratives
Artificial Intelligence (AI) systems are increasingly pervasive: Internet of Things, in-car intelligent devices, robots, and virtual …
PDF Cite DOI
Towards Personality-aware Chatbots
Chatbots are increasingly used to automate operational processes in customer service. However, most chatbots lack adaptation towards …
PDF Cite
Mediators: Conversational Agents Explaining NLP Model Behavior
The human-centric explainable artificial intelligence (HCXAI) community has raised the need for framing the explanation process as a …
PDF Cite Slides