从目标选择到条件复用：审计工具使用模型中的残差干预（Qwen3.5-27B）
From Target Selection to Condition Reuse: Auditing Residual Interventions in Tool-Use Models
AI 导读
论文在 Qwen3.5-27B 上审计激活干预能否让模型真正使用预期条件，覆盖 32 个工具使用任务环境。两种残差写入变体将熟悉目标选择的正确率从 35/128 提升到 119/128、从 33/128 提升到 114/128，但在同一任务中重组熟悉事实与标识符时增益消失，对候选是否合格的独立判断改善也很有限。
正文 · 原文
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 selection. Across 32 fresh worlds, two case-specific residual-writing variants raise familiar target-selection correctness from 35/128 to 119/128 and from 33/128 to 114/128. Yet these gains disappear when familiar facts and identifiers are recombined within the same selection task, while selection of previously rewarded identifiers increases. The gains persist across output formats but yield little improvement in independent judgments about whether a candidate is eligible or should be selected. Internal edits can nevertheless change how a source fact affects a judgment: in a prespecified secondary comparison, an early-layer source patch changes 50/64 judgments when that source is used, with one adverse change among 64 cases where it is not. This selective effect does not ensure correct complete actions. Together, these results separate target-selection control, condition-sensitive judgments, and complete-action correctness. Evaluating how an edited state is used, rather than only its trained answer, exposes these differences.
| Comments: | 21 pages, 5 figures. Code: this https URL |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.31686 [cs.CL] |
| (or arXiv:2610.31686v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31686 arXiv-issued DOI via DataCite |
Submission history
From: Tianda Sun [view email]
[v1]
Mon, 5 Oct 2026 11:46:10 UTC (48 KB)
来源：arXiv cs.AI · arxiv.org