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 scenarios. We find that efficient steering methods frequently achieve conditioning at a steep cost to fluency. Furthermore, we identify a critical yet…
Read the original at Apple machine learning research: On the Effectiveness-Fluency Trade-Off in LLM Conditioning: A Systematic Study
Source: https://machinelearning.apple.com/research/effectiveness-fluency-llm-conditioning