发表机构
Future Principle; Aarhus University（未来原理; 奥胡斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究大语言模型结合预测市场测量信息偏差，通过消融特定文本偏差贡献，应用于乌克兰相关预测市场发现英语新闻背景致偏差，主要源于文本，补充乌军事分析源可减偏差，此偏差在多架构中会持续并影响下游决策。
AI 中文摘要
每个信息生态系统都会产生影响战略决策的信念。人类分析师和人工智能系统都会继承其信息来源的盲点。我们表明，大语言模型与预测市场相结合，可作为一种校准工具，用于衡量生态系统引发的信念与外部参考之间的偏差程度：大语言模型提取文本语料库隐含的信念，预测市场价格轨迹以实际结果为锚定提供校准参考，用以量化偏差。我们通过消融来分离特定文本的偏差贡献：在保持模型不变的情况下改变信息背景，用一个知道实际结果的受污染模型作为对照。应用于111个与乌克兰相关的预测市场，涵盖四个模型的约93000个预测，我们发现英语新闻背景系统性地使领土预测产生偏差，当它将预测推向领土占领时，错误率达64%至72%。一个知道实际结果的受污染模型显示出相同的错误率，表明偏差主要源于文本。补充乌克兰军事分析来源可减少所有纯净模型中的偏差，而绝对误差的改善是部分的且依赖于模型。我们表明，这种扭曲主要源于信息来源而非模型。在四种架构中一致，它将在任何处理这些信息的系统中持续存在并传播到下游决策中。
英文摘要
Every information ecosystem produces beliefs that shape strategic decisions. Both human analysts and AI systems inherit the blind spots of their information sources. We show that LLMs, combined with prediction markets, function as a calibrated instrument for measuring how far ecosystem-induced beliefs deviate from an external reference: LLMs extract the beliefs a text corpus implies, and prediction market price trajectories, anchored at resolution by realised outcomes, provide the calibration reference against which to quantify the deviation. We isolate the bias contribution of specific text through ablation: varying information context while holding the model fixed, with a contaminated model that knows actual outcomes as control. Applied to 111 Ukraine-related prediction markets, comprising approximately 93,000 predictions across four models, we find that English news context systematically biases territorial predictions, wrong 64 to 72 percent of the time when it pushes predictions toward territorial capture. A contaminated model that knows actual outcomes shows the same error rate, indicating that the bias originates primarily in the text. Supplementing with Ukrainian military-analytical sources reduces the bias for all clean models, while absolute-error gains are partial and model-dependent. We show that the distortion originates primarily in the sources, not the models. Consistent across four architectures, it will persist in any system that processes them and propagate into downstream decisions.
CommentsAccepted at UNLP 2026. 12 pages, 8 figures, 11 tables. Dataset available at https://huggingface.co/datasets/OpenBabylon/unlp-ukraine-forecasting
