Pith. sign in

Steering large language models using conceptors: Improving addition-based activation engineering, 2025

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CL 1

years

2025 1

verdicts

REJECT 1

roles

background 1

polarities

background 1

representative citing papers

Fusion Steering: Prompt-Specific Activation Control

cs.CL · 2025-05-28 · reject · novelty 5.0

Fusion Steering tunes per-prompt activation injections against ground-truth answers and reports 25.4% accuracy on the same 260 SimpleQA prompts, a gain that is compromised by circular evaluation.

citing papers explorer

Showing 1 of 1 citing paper.

  • Fusion Steering: Prompt-Specific Activation Control cs.CL · 2025-05-28 · reject · none · ref 8

    Fusion Steering tunes per-prompt activation injections against ground-truth answers and reports 25.4% accuracy on the same 260 SimpleQA prompts, a gain that is compromised by circular evaluation.