SOURCE-LINKED INTELLIGENCE

Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

A notable byproduct of LLM alignment training is mode collapse: the progressive loss of output diversity that narrows a model's expressivity at inference time. This degradation is especially limiting for applications requiring open-ended exploration and pluralistic perspectives, such as scientific ideation and creative writing. We present MoDA (Mode-conditioned Diversity Alignment), an online post-training RL algorithm that jointly optimizes generation quality and diversity, inspired by the coordination perspective in multi-agent reinforcement learning (MARL). MoDA trains a single shared LLM p

Read original source ↗ Open in workspace

recordType

paper

region

Global