作者位次 #3/7ACL 2026Poster· Natural Language Processing
Controlling Distributional Bias in Multi-Round LLM Generation via KL -Optimized Fine-Tuning
Yanbei Jiang · Amr Keleg · Ryandito Diandaru · Jey Han Lau · Lea Frermann · Biaoyan Fang · Fajri Koto
摘要
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 adh...