# IWIBench: 评估无梯度模型驱动的权重内注入

> 全文为英语

**Published:** 2026年11月9日
**Author:** Chris von Csefalvay, Pranav Doma, Achyuthan Unni Krishnan, Tam\'as F\"oldi
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/iwibench-evaluating-gradient-free-model-driven-intra-weight-injection

arXiv:2611.08647v1 通告类型: new 摘要: 权重内注入允许一个模型通过直接编辑另一个模型的权重来改变其行为，而无需梯度。此类编辑范围可以从改变词汇关联到强制输出格式或更新事实信息…

arXiv:2611.08647v1 Announce Type: new Abstract: Intra-weight injection lets one model change another model's behaviour by editing its weights directly, without gradients. Such edits can range from altering lexical associations to enforcing output formats or updating factual knowledge. Despite growing interest in these approaches, there has been no systematic way to evaluate how well models perform them. We introduce IWIBench, which measures a large editor model's ability to modify the weights of a smaller target model (typically Gemma 3 4B IT) to achieve one of ten classical text-editing objectives while preserving its other capabilities. Editors are limited to four tools for reading and writing weights, with bounded tensor access and a fixed budget for generating and inspecting rollouts. A validator applies each proposed patch in a clean environment and compares the edited model against the unmodified target. Evaluating frontier closed- and open-weight models reveals sharply diverging capabilities, both across models and across tasks. A small number of models, most notably Astra and GPT-6.1 Sol, perform far ahead of the rest. The recency of this ability (little of it is evident in GPT-5.6 Sol, for instance), together with qualitative analysis, suggests it has been acquired through recent training. Tasks also vary widely: structured response resisted every attempt, and answer-length control yielded only one successful solution, whereas alias acquisition and recoding proved most amenable. Success in one task family correlated poorly with success in others, indicating an early and uneven capability frontier. We discuss strategies that editors repeatedly adopted and conclude with an outlook on intra-weight injection as an emerging but already potent approach to gradient-free behaviour modification.

---

*内容来自原始来源： [arXiv — cs.AI](https://arxiv.org/abs/2611.08647). 查看原文.*

**标签：** #OpenAI #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*