Sparse Internal Control of Language Models
arXiv:2611.04349v1 Announce Type: new Abstract: Language models are increasingly used in text generation, decision support, and automated interaction, creating a need for localized, reversible, and selective control of their behavior. Activation steering demonstrates that internal interventions can…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-11-04 05:00 · arXiv cs.CL
Sparse Internal Control of Language Models