Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach
May 12, 2026·
·
0 min read
Maziar Kianimoghadam Jouneghani
Abstract
Recognizing information disorder is difficult because judgments about manipulation depend on cultural and linguistic context. Yet current Large Language Models (LLMs) often behave as monocultural, English-centric “black boxes,” producing fluent rationales that overlook localized framing. Preliminary evidence from the multilingual Information Disorder (InDor) corpus suggests that existing models struggle to explain manipulated news consistently across communities. To address this gap, this ongoing study proposes a Hybrid Intelligence Loop, a human-in-the-loop (HITL) framework that grounds model assessment in human-written rationales from native-speaking annotators. The approach moves beyond static target-language few-shot prompting by pairing English task instructions with dynamically retrieved target-language exemplars drawn from filtered InDor annotations through In-Context Learning (ICL). In the initial pilot, the Exemplar Bank is seeded from these filtered annotations and used to compare static and adaptive prompting on Farsi and Italian news. The study evaluates span and severity prediction, the quality and cultural appropriateness of generated rationales, and model alignment across evaluator groups, providing a testbed for culturally grounded explainable AI.
Type
Publication
Presented at the Information Disorder Workshop (InDor26) at LREC 2026, Palma de Mallorca, Spain (Non-archival)
Authors
NLP Researcher
Hi! I’m an NLP and Computational Linguistics researcher with a Master’s degree in Language Technologies and Digital Humanities from the University of Turin, where I graduated in July 2026. I’m interested in the intersection of language, culture, and AI.
My master’s thesis, supervised by Prof. Viviana Patti and Dr. Marco Antonio Stranisci, grew out of a community-developed dataset on information disorder (InDor). It proposed a retrieval-based framework to connect LLMs’ reasoning to native-speaker explanations from InDor, based on semantic similarity, in order to align LLMs better on assessing and reasoning about manipulation signals across different cultures and languages. This framework was tested on Italian and Persian, using automatic metrics, qualitative analysis, and a human evaluation study.
My Bachelor’s degree is in English language translation, focused on linguistics and translation studies.
Also, beyond academia, I spent over 3 years in SEO, web content, and digital marketing.
My research interests are: Multilingual & Cross-Cultural NLP, Computational Social Science (CSS), Explainable AI, In-Context Learning, Human-in-the-Loop AI, and Information Disorder.
My master’s thesis, supervised by Prof. Viviana Patti and Dr. Marco Antonio Stranisci, grew out of a community-developed dataset on information disorder (InDor). It proposed a retrieval-based framework to connect LLMs’ reasoning to native-speaker explanations from InDor, based on semantic similarity, in order to align LLMs better on assessing and reasoning about manipulation signals across different cultures and languages. This framework was tested on Italian and Persian, using automatic metrics, qualitative analysis, and a human evaluation study.
My Bachelor’s degree is in English language translation, focused on linguistics and translation studies.
Also, beyond academia, I spent over 3 years in SEO, web content, and digital marketing.
My research interests are: Multilingual & Cross-Cultural NLP, Computational Social Science (CSS), Explainable AI, In-Context Learning, Human-in-the-Loop AI, and Information Disorder.