# Lifelong Knowledge Editing on GPT-2 XL (1024 Edits, test) Source: [Lifelong Knowledge Editing on GPT-2 XL (1024 Edits, test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:04:06.186Z Evaluation of Lifelong Knowledge Editing performance on the GPT-2 XL model, specifically testing 1024 edits on the test split, measured by Score, Effectiveness, Generality, Locality, and Retention metrics. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Lifelong Knowledge Editing | | Dataset (including any stated split) | Lifelong Editing on GPT-2 XL 1024 edits (test) | | Metric | Score (S) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 6 of 6 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Score (S)](): Higher is better; unit: SCALAR. - [Effectiveness (ES)](): Higher is better; unit: PERCENT. - [Generality (PS)](): Higher is better; unit: PERCENT. - [Locality (NS)](): Higher is better; unit: PERCENT. - [Retention (ERS)](): Higher is better; unit: PERCENT. - [Retention (ORS)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Score (S) | Result date | Report paper | | --- | --- | --- | --- | | WilKE | 19.3 | Not recorded | 68fa73701e209131cea5c802 | | MEMIT | 13.2 | Not recorded | 68fa73701e209131cea5c802 | | ROME | 9.3 | Not recorded | 68fa73701e209131cea5c802 | | KE | 0 | Not recorded | 68fa73701e209131cea5c802 | | KN | 0 | Not recorded | 68fa73701e209131cea5c802 | | MEND | 0 | Not recorded | 68fa73701e209131cea5c802 | ### WilKE Score (S): 19.3. Result ID: 6992eb3b3a6c314849125b7d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-2 XL (1.5B)"}. This record does not assert independent reproduction. ### MEMIT Score (S): 13.2. Result ID: 6992eb3b3a6c314849125b7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-2 XL (1.5B)"}. This record does not assert independent reproduction. ### ROME Score (S): 9.3. Result ID: 6992eb3b3a6c314849125b7b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-2 XL (1.5B)"}. This record does not assert independent reproduction. ### KE Score (S): 0. Result ID: 6992eb3b3a6c314849125b78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-2 XL (1.5B)"}. This record does not assert independent reproduction. ### KN Score (S): 0. Result ID: 6992eb3b3a6c314849125b79. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-2 XL (1.5B)"}. This record does not assert independent reproduction. ### MEND Score (S): 0. Result ID: 6992eb3b3a6c314849125b7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-2 XL (1.5B)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.