Such concerns are shared by politics and industry, leading to the adoption of France's "Loi pour une République numérique (Law for the Digital Republic)" in October 2016 (Algan et al., 2016), EU's General Data Protection Regulation in May 2018, and the California Consumer Privacy Act (Wang et al., 2022), all of which regulate data protection, collection, and processing.

Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data, they generally rely on simple class-conditional prompts, which may limit the diversity of the generated data and inherit systematic biases of LLM. Thus, we investigate training data generation with diversely attributed prompts (e.g.,

As recommended by the NeurIPS dataset and benchmark track, we documented QM1B and intended uses through the Datasheets for Datasets framework [1]. The goal of dataset datasheets as outlined by [1] is to provide a standardized process for documentating datasets. The authors of [1] present a list of carefully selected questions which dataset authors should answer. We hope our answers to these questions will facilitate better communication between us (the dataset creators) and future users of QM1B. For what purpose was the dataset created? Prior gaussian-based Density Functional Theory (DFT) datasets contained fewer than 20 million training examples.

A.1 Deriving the Optimum of the KL-Constrained Reward Maximization Objective In this appendix, we will derive Eq. 4. Analogously to Eq. 3, we optimize the following objective: max