数字民主中的 AI 对齐：应对 LLM 偏差以实现更公平的选民代表性
AI Alignment for Digital Democracy: Fairer Voters Representation against LLM Biases
Yi Qi · Srijoni Majumdar · Evangelos Pournaras
中文摘要
arXiv:2610.32780v1，公告类型：交叉研究。人工智能（AI）代表正逐步应用于数字民主，协助模拟选民并参与决策。大型语言模型（LLMs）的表现会随模型、提示上下文及所获选民信息而变化，对不同群体的模拟准确度存在差异，可能使部分选民群体受到不公平对待。研究考察 LLM 模拟选民群体的人口统计偏差，包括个体投票模拟准确度、群体间代表性差异，以及 AI 对齐能否在维持总体准确度的同时缩小差距。基于 3 次美国总统选举，比较闭源与开源 LLM，并测试面向更公平选民代表性的 AI 对齐策略。移除选民资料中的性别信息可使模型最大群体误差降低 22–42%，移除教育信息可降低 64%；移除自报种族信息则使平均群体误差增加逾 40%，且上述变化均未降低准确度。重复查询、公平性指令等常见对齐策略无法减少这些误差，甚至可能将其扩大一倍。
关键要点
- 01LLM 模拟选民受模型、提示上下文及选民资料影响，对不同人口统计群体的代表性不均。
- 02研究基于 3 次美国总统选举，比较闭源与开源 LLM 的个体投票模拟及群体偏差。
- 03移除性别信息使最大群体误差降低 22–42%，移除教育信息使其降低 64%，准确度均未下降。
- 04移除自报种族信息使平均群体误差增加逾 40%，显示人口统计特征的影响并不一致。
- 05重复查询和公平性指令未能减少群体误差，甚至可能使误差扩大一倍。
解读
尚无解读。
原始英文摘要
arXiv:2610.32780v1 Announce Type: cross Abstract: AI representation is emerging in digital democracy, assisting in voter emulation and decision-making. Large language models (LLMs) behave differently depending on the model, the prompt context, and the voter information they receive, representing some groups more accurately than others and potentially making the emulation unfair to certain groups. We investigate demographic biases in LLM-emulated electorates: how accurately LLMs represent individual votes, whether some voter groups are represented more accurately than others, and whether AI alignment can reduce these disparities without sacrificing overall accuracy. Using three U.S. presidential elections, we compare a closed-source and an open-source LLM across voters' demographic features and test AI alignment strategies toward fairer voter representation. Removing gender from the voter profile reduces the largest group error of the models by 22-42%, and removing education reduces it by 64%, whereas removing self-reported race increases the mean group error by over 40%, all without lowering accuracy. Common alignment strategies, such as repeated queries or fairness instructions, do not reduce these errors and can double them.