On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study

Excerpt

arXiv:2606.12234v2 Announce Type: replace Abstract: Controlling the output of Large Language Models (LLMs) is a central challenge for their reliable deployment, yet a clear understanding of the involved trade-offs remains elusive. Current approaches to conditioning are often evaluated with a narrow focus on their effectiveness at injecting or removing a target concept, neglecting generation quality. We systematically investigate a range of conditioning methods in both injection and removal scena