Efficient Social Choice via NLP and Sampling
This addresses the challenge of scalable governance for decentralized organizations like DAOs, though it is incremental as it builds on existing social choice and NLP techniques.
The paper tackles the problem of enabling efficient decision-making in agent communities with limited attention by combining NLP and sampling to predict proposal outcomes and decide based on a sample majority, achieving results such as a 30% reduction in voting time while maintaining 95% accuracy in DAO data.
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).