Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach

TL;DR

This paper introduces a culturally adaptive, human-in-the-loop framework for assessing multilingual information disorder with explainable AI, addressing the limitations of current English-centric LLMs.

Contribution

It proposes a Hybrid Intelligence Loop that uses native speaker rationales and dynamic exemplar retrieval to improve model explanations across cultures and languages.

Findings

Preliminary results show improved explanation quality in Farsi and Italian news.

The approach enhances model alignment with native speaker judgments.

Dynamic prompting outperforms static methods in cross-cultural contexts.

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.