Jointly Reinforcing Diversity and Quality in Language Model Generations
This addresses a key limitation for users needing diverse outputs in creative and exploratory applications, though it is an incremental improvement over existing reinforcement learning methods.
The paper tackles the problem of post-training large language models prioritizing accuracy over diversity, which limits their usefulness in creative tasks, by introducing Diversity-Aware Reinforcement Learning (DARLING) to jointly optimize for quality and semantic diversity, resulting in higher quality and novelty across benchmarks, including improved pass@1 and pass@k in competition math.
Post-training of Large Language Models (LMs) often prioritizes accuracy and helpfulness at the expense of diversity. This creates a tension: while post-training improves response quality, it also sharpens output distributions and reduces the range of ideas, limiting the usefulness of LMs in creative and exploratory tasks such as brainstorming, storytelling, or problem solving. We address this challenge with Diversity-Aware Reinforcement Learning (DARLING), a framework that jointly optimizes for response quality and semantic diversity. At its core, DARLING introduces a learned partition function to measure diversity beyond surface-level lexical variations. This diversity signal is then combined with a quality reward during online reinforcement learning, encouraging models to generate outputs that are both high-quality and distinct. Experiments across multiple model families and sizes show that DARLING generalizes to two regimes: non-verifiable tasks (instruction following and creative writing) and verifiable tasks (competition math). On five benchmarks in the first setting, DARLING consistently outperforms quality-only RL baselines, producing outputs that are simultaneously of higher quality and novelty. In the second setting, DARLING achieves higher pass@1 (solution quality) and pass@k (solution variety). Most strikingly, explicitly optimizing for diversity catalyzes exploration in online RL, which manifests itself as higher-quality responses.