Granular feedback merits sophisticated aggregation
This work addresses a cost-efficiency challenge in applications like AI training and opinion measurement, but it is incremental as it builds on existing aggregation methods.
The paper tackles the problem of predicting a population's distribution of feedback from a limited number of individuals, showing that as feedback granularity increases, sophisticated aggregation methods outperform regularized averaging, with five-point feedback requiring about half as many individuals to achieve the same performance.
Human feedback is increasingly used across diverse applications like training AI models, developing recommender systems, and measuring public opinion -- with granular feedback often being preferred over binary feedback for its greater informativeness. While it is easy to accurately estimate a population's distribution of feedback given feedback from a large number of individuals, cost constraints typically necessitate using smaller groups. A simple method to approximate the population distribution is regularized averaging: compute the empirical distribution and regularize it toward a prior. Can we do better? As we will discuss, the answer to this question depends on feedback granularity. Suppose one wants to predict a population's distribution of feedback using feedback from a limited number of individuals. We show that, as feedback granularity increases, one can substantially improve upon predictions of regularized averaging by combining individuals' feedback in ways more sophisticated than regularized averaging. Our empirical analysis using questions on social attitudes confirms this pattern. In particular, with binary feedback, sophistication barely reduces the number of individuals required to attain a fixed level of performance. By contrast, with five-point feedback, sophisticated methods match the performance of regularized averaging with about half as many individuals.