# Attribute Value Extraction on AE-pub cleaned (test) Source: [Attribute Value Extraction on AE-pub cleaned (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:51:33.137Z Evaluation of Attribute Value Extraction performance on the test split of the AE-pub cleaned dataset, reporting Macro and Micro Precision, Recall, and F1 scores. 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 | Attribute Value Extraction | | Dataset (including any stated split) | AE-pub cleaned (test) | | Metric | Macro Precision | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 - [Macro Precision](): Higher is better; unit: PERCENT. - [Macro Recall](): Higher is better; unit: PERCENT. - [Macro F1](): Higher is better; unit: PERCENT. - [Micro Precision](): Higher is better; unit: PERCENT. - [Micro Recall](): Higher is better; unit: PERCENT. - [Micro F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Macro Precision | Result date | Report paper | | --- | --- | --- | --- | | BERT-QA +vals +drop +mixing | 47.74 | Not recorded | 68fa6ce61e209131cea369fa | | BERT-QA +vals +mixing | 46.67 | Not recorded | 68fa6ce61e209131cea369fa | | BERT-QA | 42.77 | Not recorded | 68fa6ce61e209131cea369fa | | AVEQA | 41.93 | Not recorded | 68fa6ce61e209131cea369fa | | BERT-QA +vals +drop | 41.61 | Not recorded | 68fa6ce61e209131cea369fa | | BERT-QA +vals | 39.48 | Not recorded | 68fa6ce61e209131cea369fa | | Dictionary | 33.2 | Not recorded | 68fa6ce61e209131cea369fa | | SUOpenTag | 30.92 | Not recorded | 68fa6ce61e209131cea369fa | ### BERT-QA +vals +drop +mixing Macro Precision: 47.74. Result ID: 698f4b653a6c314849f7bc65. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model variant/components":"Knowledge-driven query expansion + Knowledge dropout + Knowledge token mixing","Pre-trained backbone":"BERT-base","Number of trials":"5"}. This record does not assert independent reproduction. ### BERT-QA +vals +mixing Macro Precision: 46.67. Result ID: 698f4b653a6c314849f7bc64. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model variant/components":"Knowledge-driven query expansion + Knowledge token mixing","Pre-trained backbone":"BERT-base","Number of trials":"5"}. This record does not assert independent reproduction. ### BERT-QA Macro Precision: 42.77. Result ID: 698f4b653a6c314849f7bc61. [Reporting paper]() Recorded evaluation configuration: {"Pre-trained backbone":"BERT-base","Number of trials":"5"}. This record does not assert independent reproduction. ### AVEQA Macro Precision: 41.93. Result ID: 698f4b653a6c314849f7bc60. [Reporting paper]() Recorded evaluation configuration: {"Number of trials":"5"}. This record does not assert independent reproduction. ### BERT-QA +vals +drop Macro Precision: 41.61. Result ID: 698f4b653a6c314849f7bc63. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model variant/components":"Knowledge-driven query expansion + Knowledge dropout","Pre-trained backbone":"BERT-base","Number of trials":"5"}. This record does not assert independent reproduction. ### BERT-QA +vals Macro Precision: 39.48. Result ID: 698f4b653a6c314849f7bc62. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model variant/components":"Knowledge-driven query expansion","Pre-trained backbone":"BERT-base","Number of trials":"5"}. This record does not assert independent reproduction. ### Dictionary Macro Precision: 33.2. Result ID: 698f4b653a6c314849f7bc5e. [Reporting paper]() Recorded evaluation configuration: {"Number of trials":"5"}. This record does not assert independent reproduction. ### SUOpenTag Macro Precision: 30.92. Result ID: 698f4b653a6c314849f7bc5f. [Reporting paper]() Recorded evaluation configuration: {"Number of trials":"5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.