Authors:
Manju Vallayil
1
;
Parma Nand
1
;
Wei Qi Yan
1
and
Héctor Allende-Cid
2
;
3
;
4
Affiliations:
1
School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand
;
2
Lamarr Institute for Machine Learning and Artificial Intelligence, 53115 Dortmund, Germany
;
3
Knowledge Discovery Department, Fraunhofer-Institute of Intelligent Analysis and Information Systems (IAIS), 53757 Sankt Augustin, Germany
;
4
Escuela de Ingeniería Informática, Pontificia Universidad Católica de Valparaíso, Valparaíso 2340025, Chile
Keyword(s):
Explainable AI(XAI), Automated Fact Verification (AFV), Retrieval Augmented Generation (RAG), Explainable AFV, Fact Checking.
Abstract:
This paper introduces CARAG-u, an unsupervised extension of the Context-Aware Retrieval Augmented Generation (CARAG) framework, designed to advance explainability in Automated Fact Verification (AFV) architectures. Unlike its predecessor, CARAG-u eliminates reliance on predefined thematic annotations and claim-evidence pair labels, by dynamically deriving thematic clusters and evidence pools from unstructured datasets. This innovation enables CARAG-u to balance local and global perspectives in evidence retrieval and explanation generation. We benchmark CARAG-u against Retrieval Augmented Generation (RAG) and compare it with CARAG, highlighting its unsupervised adaptability while maintaining a competitive performance. Evaluations on the FactVer dataset demonstrate CARAG-u’s ability to generate thematically coherent and context-sensitive post-hoc explanations, advancing Explainable AI in AFV. The implementation of CARAG-u, including all dependencies, is publicly available to ensure rep
roducibility and support further research.
(More)