Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach
This work addresses the need for culturally adaptive explainable AI in multilingual misinformation detection, a problem for researchers and practitioners dealing with non-English information disorder.
The study proposes a human-in-the-loop framework that uses native-speaking annotators' rationales to adapt LLM explanations for multilingual information disorder detection, addressing the cultural and linguistic biases of current models. Preliminary results show improved rationale quality and cultural appropriateness in Farsi and Italian news.
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.