跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 18 天前AI 評分54

IWIBench 評估無梯度模型驅動的權重內注入能力

IWIBench: Evaluating Gradient-Free Model Driven Intra-weight Injection

AI 導讀

IWIBench 評測大型編輯模型能否在不使用梯度的情況下修改較小目標模型的權重,以完成文本編輯並保留其其他能力。研究涵蓋十種文本編輯目標,目標模型通常為 Gemma 3 4B IT;編輯模型限用四種權重讀寫工具,並受張量存取範圍及生成、檢查 rollout 預算限制。

正文

Published on Nov 5

Authors:

,

,

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.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2611.08647

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.08647 in a model README.md to link it from this page.

Datasets citing this paper 1

hcltech-robotics/iwibench

RL Environment •

Updated about 3 hours ago

•

1.36k

•

733

•

1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.08647 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co