SOURCE-LINKED INTELLIGENCE

You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Ask a language model to respond "very excitedly," and its output is typically only mildly more energetic. We quantify this effect. We condition an instruction-tuned LLM on a continuous Valence-Arousal (VA) target, where valence measures how pleasant a state is and arousal how activated it is, measure the achieved affect with a frozen regressor, and sweep the requested target from -1 to +1. The response moves far less than asked: the gain, the slope of achieved against requested affect, is only 0.26 for valence and 0.13 for arousal on Llama-3.1-8B, where a faithful controller would score 1. The

Read original source ↗ Open in workspace

recordType

paper

region

Global