CANVAS: Adjustable Creativity Control in Large Language Models via Sparse Neuron Scaling

Large language models often produce homogeneous responses to open-ended creative requests, yet increasing variation alone does not ensure meaningful novelty. We study adjustable creativity control without retraining, addressing two challenges: distinguishing novelty from uncontrolled deviation and identifying neurons whose amplification improves creative generation. We introduce CANDLE, an evaluation framework that measures semantic and lexical deviation from the unmodified model's fixed, prompt-specific greedy response under explicit quality constraints. Building on this framework, CANVAS ranks feed-forward neurons by the estimated first-order effect of scaling on a creative-token objective, filters potentially destabilizing targets, and scales a sparse subset of weights. Intervention strength is continuously adjustable, and fixed-strength edits require no additional inference-time computation. Experiments across three model families and three creative-task categories show improved empirical novelty–quality trade-offs. CANDLE's novelty metric achieves agreement scores of $0.760$ with LLM judges and $0.669$ with human annotators. At a scaling strength of $\alpha =1.8$, CANVAS increases novelty scores by $14.13\%$ on Qwen and $19.44\%$ on Gemma, with no observed decline in mean quality. Ablations support the contributions of intervention-aligned attribution and stability safeguards. These results establish sparse neuron scaling as a practical approach to adjustable, quality-constrained creative generation.