用LLM输出概率构建分布，预测美国大选结果并分析模型偏差。
LLM Generated Distribution-Based Prediction of US Electoral Results, Part I
- 将LLM输出概率视为世界认知分布，实现新预测范式。
- 成功识别任务特定偏差与提示噪声，验证算法可靠性。
- 适合关注AI预测透明性与可信度的研究者参考。
本文提出基于分布的预测方法，通过将大型语言模型（LLM）输出的标记概率解释为模型对世界的认知分布，将其作为预测工具的新视角。该方法为分析算法保真度提供了替代方案，补充了硅基采样策略。我们以近期美国总统选举为例，展示了该方法在识别任务特定偏差、提示噪声及算法保真度方面的应用。这一框架对评估各类场景下基于LLM预测的可靠性与透明性具有重要意义。
原文摘要 · Abstract (English)
This paper introduces distribution-based prediction, a novel approach to using Large Language Models (LLMs) as predictive tools by interpreting output token probabilities as distributions representing the models' learned representation of the world. This distribution-based nature offers an alternative perspective for analyzing algorithmic fidelity, complementing the approach used in silicon sampling. We demonstrate the use of distribution-based prediction in the context of recent United States presidential election, showing that this method can be used to determine task specific bias, prompt noise, and algorithmic fidelity. This approach has significant implications for assessing the reliability and increasing transparency of LLM-based predictions across various domains.
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。