让AI理解不同文化的假新闻，用本地人写的原因来训练模型。
Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach
- 用真人撰写的本地化理由构建示例库，动态匹配目标语言
- 在波斯语和意大利语新闻上，模型解释质量提升明显
- 适合做跨文化信息治理与可解释AI的研究者
识别信息失实困难，因判断操纵行为需依赖文化与语言背景。当前大语言模型多为单一文化、以英语为中心的“黑箱”，生成流畅但忽视本地化表述。初步研究表明，现有模型在多语言信息失实数据集（InDor）上难以一致解释不同社群中的操纵新闻。为此，本研究提出一种混合智能环（Hybrid Intelligence Loop），采用人机协同框架，将模型评估基于母语标注者撰写的真实理由。该方法超越静态目标语言少样本提示，通过上下文学习（ICL）从筛选后的InDor标注中动态检索目标语言示例，结合英文任务指令使用。初步试点中，示例库源自筛选后的标注，用于对比静态与自适应提示在波斯语和意大利语新闻上的表现。评估内容包括片段与严重程度预测、生成理由的质量与文化适配性，以及不同评估群体间的模型对齐度，为文化根基的可解释AI提供测试平台。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。