文化适应性可解释LLM评估用于多语言信息紊乱：一种人机协作方法
Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach
AI总结：
本文提出一种人机协作框架，通过本地语言标注者生成的解释性理由，评估LLM在多语言信息紊乱中的表现，提升模型的文化适应性和可解释性。
摘要：
识别信息紊乱具有挑战性，因为对操纵的判断依赖于文化和语言背景。然而，当前大型语言模型（LLM）通常表现为单文化、以英语为中心的“黑箱”，产生流畅的解释但忽视本地框架。初步证据表明，现有模型在不同社区中难以一致解释操纵新闻。为此，本文提出混合智能循环框架，通过本地语言标注者生成的解释性理由来评估模型。该方法超越了静态目标语言少样本提示，通过结合英语任务指令和动态检索的目标语言示例（来自过滤后的InDor注释）进行上下文学习（ICL）。在初步试点中，示例库从这些过滤注释中构建，并用于比较静态和适应性提示在波斯语和意大利语新闻中的表现。研究评估了跨度和严重性预测、生成解释的质量和文化适当性，以及跨评估者群体的模型对齐情况，为文化导向的可解释AI提供了测试平台。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
