Nigel Collier, Zheng Hui, Tiancheng Hu, Yijiang Dong
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large language models excel at complex instructions yet struggle to deviate from their helpful assistant persona, as post-training instills strong priors that resist conflicting instructions. We introduce system prompt strength, a training-free method that treats prompt adherence as a continuous control. By contrasting logits from target and default system prompts, we isolate and amplify the behavioral signal unique to the target persona by a scalar factor α. Across five diverse benchmarks spanning constraint satisfaction, behavioral control, pluralistic alignment, capability modulation, and stylistic control, our method yields substantial improvements: up to +8.5 strict accuracy on IFEval, +45pp refusal rate on OffTopicEval, and +13% steerability on Prompt-Steering. Our approach enables practitioners to modulate system prompt strength, providing dynamic control over model behavior without retraining. Our code will be available at https: //github.com/dong-river/persona_cd.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2601.06403")
get_code_for_paper("2601.06403")
have("2601.06403")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2601.06403.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2601.06403)
Connect an agent — have() is free.