AI Alignment for Digital Democracy: Fairer Voters Representation against LLM Biases
This work investigates 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.
Yi-Rong Qi, Srijoni Majumdar, E. Pournaras
· 0 citations