# Event Argument Extraction on WikiEvents (test) Source: [Event Argument Extraction on WikiEvents (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:35:01.128Z Evaluation of Event Argument Extraction performance on the test split of the WikiEvents dataset, measured using threshold-based metrics and AUC. 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 | Event Argument Extraction | | Dataset (including any stated split) | WikiEvents (test) | | Metric | Arg-C | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Arg-C](): Higher is better; unit: PERCENT. - [Performance at 0% Threshold](): Higher is better; unit: SCALAR. - [Performance at 1% Threshold](): Higher is better; unit: SCALAR. - [Performance at 5% Threshold](): Higher is better; unit: SCALAR. - [Performance at 10% Threshold](): Higher is better; unit: SCALAR. - [Performance at 20% Threshold](): Higher is better; unit: SCALAR. - [Performance at 100% Threshold](): Higher is better; unit: SCALAR. - [AUC](): Higher is better; unit: PERCENT. - [Arg-I](): Higher is better; unit: PERCENT. ## Recorded results | Method | Arg-C | Result date | Report paper | | --- | --- | --- | --- | | DEEIA | 67 | Not recorded | 68fa73b21e209131cea5df92 | | SCPRG | 66.4 | Not recorded | 68fa73b21e209131cea5df92 | | SPEAE | 66.1 | Not recorded | 68fa73b21e209131cea5df92 | | TabEAE-multi | 66 | Not recorded | 68fa73b21e209131cea5df92 | | TSAR | 65.8 | Not recorded | 68fa73b21e209131cea5df92 | | SCPRG | 65.8 | Not recorded | 68fa73b21e209131cea5df92 | | TSAR | 65.5 | Not recorded | 68fa73b21e209131cea5df92 | | TabEAE | 65.4 | Not recorded | 68fa73b21e209131cea5df92 | | PAIE | 65.3 | Not recorded | 68fa73b21e209131cea5df92 | | RKDE | 63.8 | Not recorded | 68fa73b21e209131cea5df92 | | HRA | 63.4 | Not recorded | 68fa73b21e209131cea5df92 | | BART-Gen | 62.4 | Not recorded | 68fa73b21e209131cea5df92 | | PAIE-multi | 61.7 | Not recorded | 68fa73b21e209131cea5df92 | | EEQA | 54.5 | Not recorded | 68fa73b21e209131cea5df92 | | DocMRC | 43.3 | Not recorded | 68fa73b21e209131cea5df92 | ### DEEIA Arg-C: 67. Result ID: 699319783a6c31484913b58f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scheme":"Prompt-based multi-event","PLM":"ROBERTa-l"}. This record does not assert independent reproduction. ### SCPRG Arg-C: 66.4. Result ID: 699319783a6c31484913b584. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scheme":"Span-based single-event","PLM":"ROBERTa-l"}. This record does not assert independent reproduction. ### SPEAE Arg-C: 66.1. Result ID: 699319783a6c31484913b58b. [Reporting paper]() Recorded evaluation configuration: {"Scheme":"Prompt-based single-event","PLM":"BART-l"}. This record does not assert independent reproduction. ### TabEAE-multi Arg-C: 66. Result ID: 699319783a6c31484913b58e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scheme":"Prompt-based multi-event","PLM":"ROBERTa-l"}. This record does not assert independent reproduction. ### TSAR Arg-C: 65.8. Result ID: 699319783a6c31484913b582. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scheme":"Span-based single-event","PLM":"ROBERTa-l"}. This record does not assert independent reproduction. ### SCPRG Arg-C: 65.8. Result ID: 699319783a6c31484913b583. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scheme":"Span-based single-event","PLM":"BERT-b"}. This record does not assert independent reproduction. ### TSAR Arg-C: 65.5. Result ID: 699319783a6c31484913b581. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scheme":"Span-based single-event","PLM":"BERT-b"}. This record does not assert independent reproduction. ### TabEAE Arg-C: 65.4. Result ID: 699319783a6c31484913b58c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scheme":"Prompt-based single-event","PLM":"ROBERTa-l"}. This record does not assert independent reproduction. ### PAIE Arg-C: 65.3. Result ID: 699319783a6c31484913b58a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scheme":"Prompt-based single-event","PLM":"BART-l"}. This record does not assert independent reproduction. ### RKDE Arg-C: 63.8. Result ID: 699319783a6c31484913b589. [Reporting paper]() Recorded evaluation configuration: {"Scheme":"Prompt-based single-event","PLM":"BART-l"}. This record does not assert independent reproduction. ### HRA Arg-C: 63.4. Result ID: 699319783a6c31484913b588. [Reporting paper]() Recorded evaluation configuration: {"Scheme":"Generation single-event","PLM":"T5-l"}. This record does not assert independent reproduction. ### BART-Gen Arg-C: 62.4. Result ID: 699319783a6c31484913b587. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scheme":"Generation single-event","PLM":"BART-l"}. This record does not assert independent reproduction. ### PAIE-multi Arg-C: 61.7. Result ID: 699319783a6c31484913b58d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scheme":"Prompt-based multi-event","PLM":"BART-l"}. This record does not assert independent reproduction. ### EEQA Arg-C: 54.5. Result ID: 699319783a6c31484913b586. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scheme":"Generation single-event","PLM":"BART-l"}. This record does not assert independent reproduction. ### DocMRC Arg-C: 43.3. Result ID: 699319783a6c31484913b585. [Reporting paper]() Recorded evaluation configuration: {"Scheme":"Generation single-event","PLM":"BERT-b"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.