From Target Selection to Condition Reuse: Auditing Residual Interventions in Tool-Use Models
arXiv:2610.31686v1 Announce Type: new Abstract: Activation interventions can make a language model produce a target answer, but can the model use the intended condition in other computations? We study this question in Qwen3.5-27B on tool-use tasks where time or permissions determine eligibility and…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-26 04:00 · arXiv cs.CL
From Target Selection to Condition Reuse: Auditing Residual Interventions in Tool-Use Models