arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.03486cs.AIcs.CL
收藏

LLM生成的基于分布的美国选举结果预测,第一部分

LLM Generated Distribution-Based Prediction of US Electoral Results, Part I

Brigham Young University(杨百翰大学)

Caleb Bradshaw, Caelen Miller, Sean Warnick

AI总结:

本文提出基于分布的预测方法,利用LLM输出令牌概率作为分布来预测美国选举结果,并分析任务偏差、提示噪声和算法保真度,以提高预测可靠性和透明度。

摘要:

本文介绍了基于分布的预测,这是一种利用大型语言模型(LLMs)作为预测工具的新方法,通过将输出令牌概率解释为表示模型所学世界表征的分布。这种基于分布的特性为分析算法保真度提供了另一种视角,补充了硅采样中使用的方法。我们展示了在最近美国总统选举背景下基于分布的预测的使用,表明该方法可用于确定任务特定偏差、提示噪声和算法保真度。这种方法对于评估基于LLM的预测在各个领域的可靠性和提高其透明度具有重要意义。

英文摘要:

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.

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。

↑