Work

KnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformers

Year: 2026

Type: preprint

Abstract: Recent research has increasingly focused on understanding how Transformers store and process knowledge, as well as how this knowledge can be edited. Research work in this area is often conducted in two phases: first, phenomena are explored on individual samples. Then, when results appear promising, more statistically robust experiments follow. To support the first phase, we propose KnowledgeDebugger, a GUI-based exploration tool for knowledge localization and editing in Transformers. Our tool - inspired by LM-Debugger - offers no-code access to the methods in EasyEdit, a widely used library of state-of-the-art Knowledge Editing approaches. We demonstrate the tool's effectiveness through case studies of recent findings in this field.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2607.01000

Authors: Benz, Eric, Stöpler, Lennart, Bolik, Nikolai, Andrzejak, Artur

Institution: Heidelberg University

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7167065779

Cites:

Cited by:

Related to: