pith. sign in

arXiv preprint arXiv:2201.05337 , year=

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.CL 1

years

2026 1 2023 1

verdicts

UNVERDICTED 2

representative citing papers

Steering Language Models With Activation Engineering

cs.CL · 2023-08-20 · unverdicted · novelty 7.0

Activation Addition steers language models by adding contrastive activation vectors from prompt pairs to control high-level properties like sentiment and toxicity at inference time without training.

citing papers explorer

Showing 2 of 2 citing papers.

  • Understanding and Enforcing Weight Disentanglement in Task Arithmetic cs.AI · 2026-04-18 · unverdicted · none · ref 55

    Task-Feature Specialization explains weight disentanglement in task arithmetic and leads to orthogonality, which OrthoReg enforces to enhance performance of model composition methods.

  • Steering Language Models With Activation Engineering cs.CL · 2023-08-20 · unverdicted · none · ref 135

    Activation Addition steers language models by adding contrastive activation vectors from prompt pairs to control high-level properties like sentiment and toxicity at inference time without training.