Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding
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 alpha. 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Continuous ControlSimilar Papers 제목 키워드 기반
Beyond Multiple Choice: Evaluating Steering Vectors for Adaptive Free-Form Summarization
Steering vectors are a lightweight method for controlling text properties by adding a learned bias to language model activations at inference time. So far, steering vectors have predominantly been evaluated in multiple-c…
FormLanguage ModelingLanguage ModellingMultiple-choiceProgramming Refusal with Conditional Activation Steering
LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicabi…
Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
Activation steering has emerged as a promising alternative for controlling language-model behavior at inference time by modifying intermediate representations while keeping model parameters frozen. However, large-scale e…
CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark
Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inf…
Detecting and Controlling Sycophancy with Cascading Linear Features
Interpreting and controlling model behaviors through activation steering methods requires many pairs of contrastive samples that clearly exhibit desired or undesired behavior. These data pairs determine the degree to whi…