PSR models that estimate token-specific steering coefficients from activations outperform standard activation steering and compare favorably to prompting on steering benchmarks.
In-distribution steering: Bal- ancing control and coherence in language model generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Prefill-Time Intervention (PTI) reduces hallucinations in large vision-language models by applying a one-time modality-aware steering correction to the initial KV cache at the prefill stage rather than during autoregressive decoding.
citing papers explorer
-
Steer Like the LLM: Activation Steering that Mimics Prompting
PSR models that estimate token-specific steering coefficients from activations outperform standard activation steering and compare favorably to prompting on steering benchmarks.