Efficient Social Choice via NLP and Sampling

TL;DR

This paper introduces a novel approach combining NLP and sampling techniques to enable efficient social decision-making in communities with limited attention, demonstrated through evaluations on DAO data.

Contribution

It proposes a new system that uses NLP to estimate proposal pass probabilities and sampling to make decisions, improving attention-aware social choice processes.

Findings

NLP models can accurately estimate proposal pass likelihoods.

Sampling-based decision methods reduce the need for full community voting.

Algorithms perform well on DAO data, showing practical effectiveness.

Abstract

Attention-Aware Social Choice tackles the fundamental conflict faced by some agent communities between their desire to include all members in the decision making processes and the limited time and attention that are at the disposal of the community members. Here, we investigate a combination of two techniques for attention-aware social choice, namely Natural Language Processing (NLP) and Sampling. Essentially, we propose a system in which each governance proposal to change the status quo is first sent to a trained NLP model that estimates the probability that the proposal would pass if all community members directly vote on it; then, based on such an estimation, a population sample of a certain size is being selected and the proposal is decided upon by taking the sample majority. We develop several concrete algorithms following the scheme described above and evaluate them using various data, including such from several Decentralized Autonomous Organizations (DAOs).