Papers › Resolving Lexical Bias in Edit Scoping with Projector Editor Networks

Resolving Lexical Bias in Edit Scoping with Projector Editor Networks

19 Aug 2024arXiv:2408.10411archive 2025-07-28

Hammad Rizwan, Domenic Rosati, Ga Wu, Hassan Sajjad

Weight-preserving model editing techniques heavily rely on the scoping mechanism that decides when to apply an edit to the base model. These scoping mechanisms utilize distance functions in the representation space to ascertain the scope of the edit. In this work, we show that distance-based scoping functions grapple with lexical biases leading to issues such as misfires with irrelevant prompts that share similar lexical characteristics. To address this problem, we introduce, Projector Editor Networks for Model Editing (PENME),is a model editing approach that employs a compact adapter with a projection network trained via a contrastive learning objective. We demonstrate the efficacy of PENME in achieving superior results while being compute efficient and flexible to adapt across model architectures.

PaperPDFCode

Code

hammadrizwan/PENME officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningModel Editing

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdapterBASEContrastive Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections