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

Chris von Csefalvay, Pranav Doma, Achyuthan Unni Krishnan, Tamás Földi

IWIBench: Evaluating Gradient-Free Model Driven Intra-weight Injection: 4 upvotes on Hugging Face Daily Papers, #28 of 34 papers on 2026-11-09. Day-by-day upvote history.

Upvotes over time

It had 3 upvotes by its first day, 4 upvotes by the next day, 4 upvotes by day 3, 4 upvotes by day 7, and has 4 now. It ranked #83 of 133 papers in its week and #244 of 340 in its month. Its code repository has 1 GitHub stars.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.