KnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformers
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownengineering87/llm-atlas →
- LinkedLinked via unknownAgentTrace →
- PossiblePossibly related (embedding) · 50%vitali87/code-graph-rag →
- LinkedLinked via arxiv author · 85%Eric Benz →
“KnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformers”
- LinkedLinked via arxiv author · 85%Lennart Stöpler →
“KnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformers”
- LinkedLinked via arxiv author · 85%Nikolai Bolik →
“KnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformers”
- LinkedLinked via arxiv author · 85%Artur Andrzejak →
“KnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformers”
- PossiblePossibly related (embedding) · 57%zjunlp/EasyEdit →