Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Unveiling the Pitfalls of Knowledge Editing for Large Language Models
2024-02-02
· ICLR 2024 poster ·
anchor
Findings
IC-1232
GPT-2 XL and GPT-J exhibit knowledge conflict when subjected to reverse and composite knowledge edits, with ROME and MEMIT showing near-total failure on reverse edits
IC-1233
GPT-2 XL and GPT-J exhibit irreversible knowledge distortion after round-editing, with the effect being more severe when the edit target is semantically distant from the true labels