arXiv cs.CY· Yi Qi, Srijoni Majumdar, Evangelos Pournaras·· 12 小时前AI 评分35
面向数字民主的 AI 对齐：用更公平的选民代表对抗 LLM 偏见
AI Alignment for Digital Democracy: Fairer Voters Representation against LLM Biases
AI 导读
研究基于三届美国总统选举，比较闭源与开源 LLM 在模拟选民时的人口统计偏见，并测试 AI 对齐策略能否在不牺牲整体准确率的前提下缩小群体差异。从选民画像中移除性别可使模型最大群体误差降低 22-42%，移除教育程度可降低 64%，而移除自报种族反而使平均群体误差上升超 40%。重复查询、公平性指令等常见对齐策略无法降低这些误差，甚至可能使其翻倍。
正文 · 原文
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.
| Subjects: | Computers and Society (cs.CY); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32780 [cs.CY] |
| (or arXiv:2610.32780v1 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32780 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yi Qi [view email]
[v1]
Fri, 23 Oct 2026 15:27:40 UTC (1,259 KB)
来源：arXiv cs.CY · arxiv.org