AI RESEARCH

Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context

arXiv CS.CL

ArXi:2604.20216v1 Announce Type: new Many applications of LLM-based text regression require predicting a full conditional distribution rather than a single point value. We study distributional regression under empirical-quantile supervision, where each input is paired with multiple observed quantile outcomes, and the target distribution is represented by a dense grid of quantiles.