# Lifelong Knowledge Editing on ZsRE Source: [Lifelong Knowledge Editing on ZsRE]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:02:05.585Z Evaluation of Knowledge Editing performance on the ZsRE dataset, specifically focusing on the lifelong editing capability. 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) | ZsRE | | Metric | Reliability | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Reliability](): Higher is better; unit: PERCENT. - [Generalization](): Higher is better; unit: PERCENT. - [Locality](): Higher is better; unit: PERCENT. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Reliability | Result date | Report paper | | --- | --- | --- | --- | | EtCon | 73.5 | Not recorded | 69326701d6b0dd334293424a | | EtCon | 69.4 | Not recorded | 69326701d6b0dd334293424a | | ALPHAEDIT | 18.7 | Not recorded | 69326701d6b0dd334293424a | | FT-M | 16.6 | Not recorded | 69326701d6b0dd334293424a | | ALPHAEDIT | 15.9 | Not recorded | 69326701d6b0dd334293424a | | FT-M | 5.6 | Not recorded | 69326701d6b0dd334293424a | | GRACE | 5.5 | Not recorded | 69326701d6b0dd334293424a | | GRACE | 4.8 | Not recorded | 69326701d6b0dd334293424a | | WISE | 4.5 | Not recorded | 69326701d6b0dd334293424a | | Pre-edit | 4.4 | Not recorded | 69326701d6b0dd334293424a | | WISE | 4.3 | Not recorded | 69326701d6b0dd334293424a | | Pre-edit | 2.8 | Not recorded | 69326701d6b0dd334293424a | | MEMIT | 0.1 | Not recorded | 69326701d6b0dd334293424a | | MEMIT | 0 | Not recorded | 69326701d6b0dd334293424a | ### EtCon Reliability: 73.5. Result ID: 6996ccaa5698665ec4188a3a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### EtCon Reliability: 69.4. Result ID: 6996ccaa5698665ec4188a33. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### ALPHAEDIT Reliability: 18.7. Result ID: 6996ccaa5698665ec4188a37. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### FT-M Reliability: 16.6. Result ID: 6996ccaa5698665ec4188a35. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### ALPHAEDIT Reliability: 15.9. Result ID: 6996ccaa5698665ec4188a30. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### FT-M Reliability: 5.6. Result ID: 6996ccaa5698665ec4188a2e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### GRACE Reliability: 5.5. Result ID: 6996ccaa5698665ec4188a39. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### GRACE Reliability: 4.8. Result ID: 6996ccaa5698665ec4188a32. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### WISE Reliability: 4.5. Result ID: 6996ccaa5698665ec4188a31. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Pre-edit Reliability: 4.4. Result ID: 6996ccaa5698665ec4188a2d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### WISE Reliability: 4.3. Result ID: 6996ccaa5698665ec4188a38. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### Pre-edit Reliability: 2.8. Result ID: 6996ccaa5698665ec4188a34. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### MEMIT Reliability: 0.1. Result ID: 6996ccaa5698665ec4188a36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### MEMIT Reliability: 0. Result ID: 6996ccaa5698665ec4188a2f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.