# Topic Classification on Yahoo Answers (test) Source: [Topic Classification on Yahoo Answers (test)]() Collection index: [llms.txt]() Data updated: 2026-05-14T06:34:43.134Z Evaluation of Topic Classification performance on the test split of the Yahoo Answers dataset, measured using specific Top-K accuracy 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 | Topic Classification | | Dataset (including any stated split) | Yahoo Answers (test) | | Metric | F1 Score (Test) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [F1 Score (Test)](): Higher is better; unit: PERCENT. - [Top-2 Accuracy (Test)](): Higher is better; unit: PERCENT. - [Top-3 Accuracy (Test)](): Higher is better; unit: PERCENT. - [Top-4 Accuracy (Test)](): Higher is better; unit: PERCENT. - [Top-5 Accuracy (Test)](): Higher is better; unit: PERCENT. - [Top-7 Accuracy (Test)](): Higher is better; unit: PERCENT. - [Top-9 Accuracy (Test)](): Higher is better; unit: PERCENT. - [Reference Test Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score (Test) | Result date | Report paper | | --- | --- | --- | --- | | SPoT | 61.3 | Not recorded | 68fa79c51e209131cea7f44a | | Task Prompt Vectors | 61.1 | Not recorded | 68fa79c51e209131cea7f44a | | SPoT | 60.7 | Not recorded | 68fa79c51e209131cea7f44a | | SPoT | 36.5 | Not recorded | 68fa79c51e209131cea7f44a | | Random | 27.6 | Not recorded | 68fa79c51e209131cea7f44a | | ATTEMPT | 8.1 | Not recorded | 68fa79c51e209131cea7f44a | | ATTEMPT | 0.1 | Not recorded | 68fa79c51e209131cea7f44a | | Random | 0 | Not recorded | 68fa79c51e209131cea7f44a | | SPoT | 0 | Not recorded | 68fa79c51e209131cea7f44a | | SPoT | 0 | Not recorded | 68fa79c51e209131cea7f44a | | SPoT | 0 | Not recorded | 68fa79c51e209131cea7f44a | | Task Prompt Vectors | 0 | Not recorded | 68fa79c51e209131cea7f44a | ### SPoT F1 Score (Test): 61.3. Result ID: 6a056d0047f34ce924ebba14. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Source tasks":"DBPedia","Number of shots":"100 shots"}. This record does not assert independent reproduction. ### Task Prompt Vectors F1 Score (Test): 61.1. Result ID: 6a056d0047f34ce924ebba1c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Source tasks":"DBPedia + TREC","Number of shots":"100 shots"}. This record does not assert independent reproduction. ### SPoT F1 Score (Test): 60.7. Result ID: 6a056d0047f34ce924ebba18. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Source tasks":"DBPedia + TREC","Number of shots":"100 shots"}. This record does not assert independent reproduction. ### SPoT F1 Score (Test): 36.5. Result ID: 6a056d0047f34ce924ebba16. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Source tasks":"TREC","Number of shots":"100 shots"}. This record does not assert independent reproduction. ### Random F1 Score (Test): 27.6. Result ID: 6a056d0047f34ce924ebba12. [Reporting paper]() Recorded evaluation configuration: {"Source tasks":"Random","Number of shots":"100 shots"}. This record does not assert independent reproduction. ### ATTEMPT F1 Score (Test): 8.1. Result ID: 6a056d0047f34ce924ebba1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Source tasks":"DBPedia + TREC","Number of shots":"100 shots"}. This record does not assert independent reproduction. ### ATTEMPT F1 Score (Test): 0.1. Result ID: 6a056d0047f34ce924ebba19. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Source tasks":"DBPedia + TREC","Number of shots":"0 shots"}. This record does not assert independent reproduction. ### Random F1 Score (Test): 0. Result ID: 6a056d0047f34ce924ebba11. [Reporting paper]() Recorded evaluation configuration: {"Source tasks":"Random","Number of shots":"0 shots"}. This record does not assert independent reproduction. ### SPoT F1 Score (Test): 0. Result ID: 6a056d0047f34ce924ebba13. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Source tasks":"DBPedia","Number of shots":"0 shots"}. This record does not assert independent reproduction. ### SPoT F1 Score (Test): 0. Result ID: 6a056d0047f34ce924ebba15. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Source tasks":"TREC","Number of shots":"0 shots"}. This record does not assert independent reproduction. ### SPoT F1 Score (Test): 0. Result ID: 6a056d0047f34ce924ebba17. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Source tasks":"DBPedia + TREC","Number of shots":"0 shots"}. This record does not assert independent reproduction. ### Task Prompt Vectors F1 Score (Test): 0. Result ID: 6a056d0047f34ce924ebba1b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Source tasks":"DBPedia + TREC","Number of shots":"0 shots"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.