# Lifelong Knowledge Editing on QAEdit Source: [Lifelong Knowledge Editing on QAEdit]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:02:05.623Z Evaluation of Lifelong Knowledge Editing performance on the QAEdit dataset, measured using Reliability, Generalization, Locality, and Average 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) | QAEdit | | Metric | Reliability | | Unit | SCALAR | | 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: SCALAR. - [Generalization](): Higher is better; unit: SCALAR. - [Locality](): Higher is better; unit: SCALAR. - [Average Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Reliability | Result date | Report paper | | --- | --- | --- | --- | | EtCon | 75.1 | Not recorded | 69326701d6b0dd334293424a | | EtCon | 70.7 | Not recorded | 69326701d6b0dd334293424a | | FT-M | 34.1 | Not recorded | 69326701d6b0dd334293424a | | ALPHAEDIT | 18.2 | Not recorded | 69326701d6b0dd334293424a | | GRACE | 15.4 | Not recorded | 69326701d6b0dd334293424a | | FT-M | 14.6 | Not recorded | 69326701d6b0dd334293424a | | GRACE | 14.2 | Not recorded | 69326701d6b0dd334293424a | | Pre-edit | 12.7 | Not recorded | 69326701d6b0dd334293424a | | Pre-edit | 9.8 | Not recorded | 69326701d6b0dd334293424a | | WISE | 8.1 | Not recorded | 69326701d6b0dd334293424a | | WISE | 7.1 | Not recorded | 69326701d6b0dd334293424a | | MEMIT | 0.4 | Not recorded | 69326701d6b0dd334293424a | | MEMIT | 0.2 | Not recorded | 69326701d6b0dd334293424a | | ALPHAEDIT | 0 | Not recorded | 69326701d6b0dd334293424a | ### EtCon Reliability: 75.1. Result ID: 6996ccaa5698665ec4188a4f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### EtCon Reliability: 70.7. Result ID: 6996ccaa5698665ec4188a56. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### FT-M Reliability: 34.1. Result ID: 6996ccaa5698665ec4188a51. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### ALPHAEDIT Reliability: 18.2. Result ID: 6996ccaa5698665ec4188a53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### GRACE Reliability: 15.4. Result ID: 6996ccaa5698665ec4188a55. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### FT-M Reliability: 14.6. Result ID: 6996ccaa5698665ec4188a4a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### GRACE Reliability: 14.2. Result ID: 6996ccaa5698665ec4188a4e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Pre-edit Reliability: 12.7. Result ID: 6996ccaa5698665ec4188a50. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### Pre-edit Reliability: 9.8. Result ID: 6996ccaa5698665ec4188a49. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### WISE Reliability: 8.1. Result ID: 6996ccaa5698665ec4188a54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### WISE Reliability: 7.1. Result ID: 6996ccaa5698665ec4188a4d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### MEMIT Reliability: 0.4. Result ID: 6996ccaa5698665ec4188a4b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### MEMIT Reliability: 0.2. Result ID: 6996ccaa5698665ec4188a52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct"}. This record does not assert independent reproduction. ### ALPHAEDIT Reliability: 0. Result ID: 6996ccaa5698665ec4188a4c. [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.