Publications

Citation

BibTex format

@inproceedings{Vasileiou:2023,
author = {Vasileiou, SL and Kumar, A and Yeoh, W and Son, TC and Toni, F},
title = {DR-HAI: argumentation-based dialectical reconciliation in human-AI interactions},
url = {http://hdl.handle.net/10044/1/104816},
year = {2023}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - In this paper, we introduce DR-HAI – a novelargumentation-based framework designed to extend model reconciliation approaches, commonlyused in explainable AI planning, for enhancedhuman-AI interaction. By adopting a multi-shotreconciliation paradigm and not assuming a-prioriknowledge of the human user’s model, DR-HAI enables interactive reconciliation to address knowledge discrepancies between an explainer and an explainee. We formally describe the operational semantics of DR-HAI, and provide theoretical guarantees related to termination and success
AU  - Vasileiou,SL
AU  - Kumar,A
AU  - Yeoh,W
AU  - Son,TC
AU  - Toni,F
PY  - 2023///
TI  - DR-HAI: argumentation-based dialectical reconciliation in human-AI interactions
UR  - http://hdl.handle.net/10044/1/104816
ER  -
Download