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

Source: arXiv - 2606.12234v1

Overview

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 previously overlooked interaction with the training paradigm: activation steering methods are far less effective on instruction-tuned models than on their base counterparts. Simple prompting and full-fledged supervised fine-tuning, on the other hand, are viable options for concept injection, but are not as good at concept removal. Finally, cheaply computed textual metrics highly correlate to costly LLM-as-judge scores, and provide insights on the behavior of conditioning methods.

Key Contributions

This paper presents research in the following areas:

• cs.CL

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.CL.

Authors

• Iuri Macocco
• Pau Rodríguez
• Arno Blaas
• Luca Zappella
• Marco Baroni
• Xavier Suau

Paper Information

• arXiv ID: 2606.12234v1
• Categories: cs.CL
• Published: June 10, 2026
• PDF: Download PDF