On the Effectiveness-Fluency Trade-Off in LLM Conditioning: A Systematic Study

This post systematically studies the effectiveness-fluency trade-off in LLM conditioning methods, identifying that efficient steering methods often come at a cost to fluency. It also highlights a critical interaction with training paradigms, showing that activation steering is less effective on instruction-tuned models. The study finds that simple prompting and supervised fine-tuning are viable for concept injection but not removal, and that textual metrics correlate with LLM-as-judge scores.