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.
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 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Fusion Steering: Prompt-Specific Activation Control
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.