A Knowledge Graph Based Diagnostic Framework for Analyzing Hallucinations in Arabic Machine Reading Comprehension

Najwa Abdullah AlGhamdi, Sadam Al-Azani, Kwabena Nuamah, Alan Bundy


Abstract
Large Language Models (LLMs) frequently generate answers that are fluent but not fully grounded in the provided context, a phenomenon commonly referred to as hallucination. While recent work has explored hallucination detection primarily in English and open domain settings, comparatively little attention has been given to Arabic machine reading comprehension (MRC), particularly in culturally sensitive domains such as Qur’anic texts. In this paper, we present a knowledge graph based diagnostic framework for analyzing hallucinations and question misalignment in Arabic MRC. Rather than proposing a new detection model or metric, the framework provides an interpretable, triple level analysis of model generated answers by comparing subject-relation-object representations derived from the passage, the question, and the answer. The approach incorporates question-aware filtering and operates under weak supervision, combining automatic analysis with targeted human adjudication to handle annotation gaps and semantic ambiguity. We apply the framework to the Qur’anic Reading Comprehension Dataset (QRCD) and demonstrate how it exposes systematic hallucination patterns that are difficult to capture using surface level similarity metrics alone, particularly for questions requiring justification or abstract interpretation. The results highlight the value of structured, transparent diagnostic evaluation for understanding LLM behavior in low resource and high stakes Arabic NLP settings.
Anthology ID:
2026.abjadnlp-1.49
Volume:
Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script
Month:
March
Year:
2026
Address:
Rabat, Morocco
Venues:
AbjadNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
413–421
Language:
URL:
https://aclanthology.org/2026.abjadnlp-1.49/
DOI:
Bibkey:
Cite (ACL):
Najwa Abdullah AlGhamdi, Sadam Al-Azani, Kwabena Nuamah, and Alan Bundy. 2026. A Knowledge Graph Based Diagnostic Framework for Analyzing Hallucinations in Arabic Machine Reading Comprehension. In Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script, pages 413–421, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
A Knowledge Graph Based Diagnostic Framework for Analyzing Hallucinations in Arabic Machine Reading Comprehension (AlGhamdi et al., AbjadNLP 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.abjadnlp-1.49.pdf