# Fine-grained Knowledge Recall on UnFine-MQ Source: [Fine-grained Knowledge Recall on UnFine-MQ]() Collection index: [llms.txt]() Data updated: 2026-04-15T09:02:36.116Z Evaluation of Fine-grained Knowledge Recall performance on the UnFine-MQ 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-MQ | | Metric | Bert-Score | | 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 - [Bert-Score](): Higher is better; unit: SCALAR. - [Rouge-L](): Higher is better; unit: SCALAR. - [HR](): Higher is better; unit: SCALAR. - [CLCS](): Higher is better; unit: SCALAR. ## Recorded results | Method | Bert-Score | Result date | Report paper | | --- | --- | --- | --- | | FABLE | 66.99 | Not recorded | 69df1b827d0172140ec7b8b2 | | FABLE | 53.16 | Not recorded | 69df1b827d0172140ec7b8b2 | | UnKE | 30.27 | Not recorded | 69df1b827d0172140ec7b8b2 | | AnyEdit | 29.96 | Not recorded | 69df1b827d0172140ec7b8b2 | | AnyEdit | 29.48 | Not recorded | 69df1b827d0172140ec7b8b2 | | UnKE | 29.31 | Not recorded | 69df1b827d0172140ec7b8b2 | | MEMIT | 29.22 | Not recorded | 69df1b827d0172140ec7b8b2 | | ROME | 28.66 | Not recorded | 69df1b827d0172140ec7b8b2 | | MEMIT | 28.54 | Not recorded | 69df1b827d0172140ec7b8b2 | | Pre-edited | 28.28 | Not recorded | 69df1b827d0172140ec7b8b2 | | FT-L | 28.04 | Not recorded | 69df1b827d0172140ec7b8b2 | | ROME | 28.01 | Not recorded | 69df1b827d0172140ec7b8b2 | | Pre-edited | 27.74 | Not recorded | 69df1b827d0172140ec7b8b2 | | FT-L | 27.27 | Not recorded | 69df1b827d0172140ec7b8b2 | ### FABLE Bert-Score: 66.99. Result ID: 69df531347f34ce924c83d21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### FABLE Bert-Score: 53.16. Result ID: 69df531347f34ce924c83d28. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### UnKE Bert-Score: 30.27. Result ID: 69df531347f34ce924c83d1f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### AnyEdit Bert-Score: 29.96. Result ID: 69df531347f34ce924c83d20. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### AnyEdit Bert-Score: 29.48. Result ID: 69df531347f34ce924c83d27. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### UnKE Bert-Score: 29.31. Result ID: 69df531347f34ce924c83d26. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### MEMIT Bert-Score: 29.22. Result ID: 69df531347f34ce924c83d1e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### ROME Bert-Score: 28.66. Result ID: 69df531347f34ce924c83d24. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### MEMIT Bert-Score: 28.54. Result ID: 69df531347f34ce924c83d25. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### Pre-edited Bert-Score: 28.28. Result ID: 69df531347f34ce924c83d22. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### FT-L Bert-Score: 28.04. Result ID: 69df531347f34ce924c83d1c. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### ROME Bert-Score: 28.01. Result ID: 69df531347f34ce924c83d1d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### Pre-edited Bert-Score: 27.74. Result ID: 69df531347f34ce924c83d1b. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction. ### FT-L Bert-Score: 27.27. Result ID: 69df531347f34ce924c83d23. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.