STA selects sparse autoencoder features by activation amplitude and frequency to build steering vectors that improve LLM safety control over prompt engineering and standard steering.
LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
As large language models (LLMs) show impressive performance on complex tasks, they still struggle with longer contextual understanding and high computational costs. To balance efficiency and quality, we introduce LLMSteer, a fine-tuning-free framework that enhances LLMs through query-independent attention steering. Tested on popular LLMs and datasets, LLMSteer narrows the performance gap with baselines by 65.9% and reduces the runtime delay by up to 4.8x compared to recent attention steering methods.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms
STA selects sparse autoencoder features by activation amplitude and frequency to build steering vectors that improve LLM safety control over prompt engineering and standard steering.