AI RESEARCH
Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning
arXiv CS.CL
•
ArXi:2604.05756v1 Announce Type: new While the real world is inherently stochastic, Large Language Models (LLMs) are predominantly evaluated on single-round inference against fixed ground truths. In this work, we shift the lens to distribution alignment: assessing whether LLMs, when prompted repeatedly, can generate outputs that adhere to a desired target distribution, e.g. reflecting real-world statistics or a uniform distribution. We formulate distribution alignment using the attributes of gender, race, and sentiment within occupational contexts.