# Fine-grained Knowledge Recall on UnFine-UnKE Source: [Fine-grained Knowledge Recall on UnFine-UnKE]() Collection index: [llms.txt]() Data updated: 2026-04-15T09:02:35.999Z Evaluation of Fine-grained Knowledge Recall performance on the UnFine-UnKE dataset, measured using Bert-Score, Rouge-L, HR, and CLCS. 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 | Fine-grained Knowledge Recall | | Dataset (including any stated split) | UnFine-UnKE | | Metric | Bert-Score | | 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 - [Bert-Score](): Higher is better; unit: PERCENT. - [Rouge-L](): Higher is better; unit: PERCENT. - [HR](): Higher is better; unit: PERCENT. - [CLCS](): Higher is better; unit: PERCENT. ## Recorded results | Method | Bert-Score | Result date | Report paper | | --- | --- | --- | --- | | FABLE | 65.63 | Not recorded | 69df1b827d0172140ec7b8b2 | | FABLE | 50.87 | Not recorded | 69df1b827d0172140ec7b8b2 | | AnyEdit | 28.61 | Not recorded | 69df1b827d0172140ec7b8b2 | | UnKE | 27.93 | Not recorded | 69df1b827d0172140ec7b8b2 | | AnyEdit | 27.75 | Not recorded | 69df1b827d0172140ec7b8b2 | | UnKE | 26.89 | Not recorded | 69df1b827d0172140ec7b8b2 | | FT-L | 26.1 | Not recorded | 69df1b827d0172140ec7b8b2 | | MEMIT | 25.6 | Not recorded | 69df1b827d0172140ec7b8b2 | | ROME | 25.59 | Not recorded | 69df1b827d0172140ec7b8b2 | | MEMIT | 25.33 | Not recorded | 69df1b827d0172140ec7b8b2 | | ROME | 24.76 | Not recorded | 69df1b827d0172140ec7b8b2 | | Pre-edited | 23.75 | Not recorded | 69df1b827d0172140ec7b8b2 | | FT-L | 23.34 | Not recorded | 69df1b827d0172140ec7b8b2 | | Pre-edited | 22.26 | Not recorded | 69df1b827d0172140ec7b8b2 | ### FABLE Bert-Score: 65.63. Result ID: 69df531347f34ce924c83ce9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### FABLE Bert-Score: 50.87. Result ID: 69df531347f34ce924c83cf0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### AnyEdit Bert-Score: 28.61. Result ID: 69df531347f34ce924c83ce8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### UnKE Bert-Score: 27.93. Result ID: 69df531347f34ce924c83ce7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### AnyEdit Bert-Score: 27.75. Result ID: 69df531347f34ce924c83cef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### UnKE Bert-Score: 26.89. Result ID: 69df531347f34ce924c83cee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### FT-L Bert-Score: 26.1. Result ID: 69df531347f34ce924c83ce4. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### MEMIT Bert-Score: 25.6. Result ID: 69df531347f34ce924c83ce6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### ROME Bert-Score: 25.59. Result ID: 69df531347f34ce924c83cec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### MEMIT Bert-Score: 25.33. Result ID: 69df531347f34ce924c83ced. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### ROME Bert-Score: 24.76. Result ID: 69df531347f34ce924c83ce5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### Pre-edited Bert-Score: 23.75. Result ID: 69df531347f34ce924c83cea. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### FT-L Bert-Score: 23.34. Result ID: 69df531347f34ce924c83ceb. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### Pre-edited Bert-Score: 22.26. Result ID: 69df531347f34ce924c83ce3. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.