# Keyphrase Extraction on WikiHow Source: [Keyphrase Extraction on WikiHow]() Collection index: [llms.txt]() Data updated: 2026-05-04T09:06:27.447Z Evaluation of Keyphrase Extraction performance on the WikiHow dataset, typically measured using F1 scores at various cutoffs (e.g., F1@5, F1@10). 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 | Keyphrase Extraction | | Dataset (including any stated split) | WikiHow | | Metric | F1@5 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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@5](): Higher is better; unit: PERCENT. - [F1@10](): Higher is better; unit: PERCENT. - [F1@15](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1@5 | Result date | Report paper | | --- | --- | --- | --- | | YAKE | 18.61 | Not recorded | 69f827e2c0f56ed8430888ab | | MultipartiteRank | 17.89 | Not recorded | 69f827e2c0f56ed8430888ab | | TopicRank | 16.77 | Not recorded | 69f827e2c0f56ed8430888ab | | MUDY | 16.59 | Not recorded | 69f827e2c0f56ed8430888ab | | MUDY | 16.59 | Not recorded | 69f827e2c0f56ed8430888ab | | MUDY | 15.54 | Not recorded | 69f827e2c0f56ed8430888ab | | MUDY | 15.54 | Not recorded | 69f827e2c0f56ed8430888ab | | MDERank | 15.25 | Not recorded | 69f827e2c0f56ed8430888ab | | PromptRank | 14.9 | Not recorded | 69f827e2c0f56ed8430888ab | | JointGL | 13.02 | Not recorded | 69f827e2c0f56ed8430888ab | | PromptRank | 12.48 | Not recorded | 69f827e2c0f56ed8430888ab | | GPT-5 | 11.91 | Not recorded | 69f827e2c0f56ed8430888ab | | Empirical | 10.97 | Not recorded | 69f827e2c0f56ed8430888ab | | GPT-5 | 9.98 | Not recorded | 69f827e2c0f56ed8430888ab | | Attention-Seeker | 8.65 | Not recorded | 69f827e2c0f56ed8430888ab | | SAMRank | 8.16 | Not recorded | 69f827e2c0f56ed8430888ab | | SingleRank | 7.59 | Not recorded | 69f827e2c0f56ed8430888ab | | TextRank | 2.91 | Not recorded | 69f827e2c0f56ed8430888ab | | EmbedRank | 2.35 | Not recorded | 69f827e2c0f56ed8430888ab | ### YAKE F1@5: 18.61. Result ID: 69f8619247f34ce924dc4d53. [Reporting paper]() Recorded evaluation configuration: {"Method Type":"Statistic-based"}. This record does not assert independent reproduction. ### MultipartiteRank F1@5: 17.89. Result ID: 69f8619247f34ce924dc4d57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Type":"Graph-based"}. This record does not assert independent reproduction. ### TopicRank F1@5: 16.77. Result ID: 69f8619247f34ce924dc4d56. [Reporting paper]() Recorded evaluation configuration: {"Method Type":"Graph-based"}. This record does not assert independent reproduction. ### MUDY F1@5: 16.59. Result ID: 69f8619247f34ce924dc4d3b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Gemma2"}. This record does not assert independent reproduction. ### MUDY F1@5: 16.59. Result ID: 69f8619247f34ce924dc4d61. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Type":"Prompt-based","Backbone":"Gemma2"}. This record does not assert independent reproduction. ### MUDY F1@5: 15.54. Result ID: 69f8619247f34ce924dc4d3a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"T5"}. This record does not assert independent reproduction. ### MUDY F1@5: 15.54. Result ID: 69f8619247f34ce924dc4d5f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Type":"Prompt-based","Backbone":"T5"}. This record does not assert independent reproduction. ### MDERank F1@5: 15.25. Result ID: 69f8619247f34ce924dc4d5a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Type":"Embedding-based","Backbone":"BERT"}. This record does not assert independent reproduction. ### PromptRank F1@5: 14.9. Result ID: 69f8619247f34ce924dc4d60. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Type":"Prompt-based","Backbone":"Gemma2"}. This record does not assert independent reproduction. ### JointGL F1@5: 13.02. Result ID: 69f8619247f34ce924dc4d59. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Type":"Embedding-based","Backbone":"BERT"}. This record does not assert independent reproduction. ### PromptRank F1@5: 12.48. Result ID: 69f8619247f34ce924dc4d5e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Type":"Prompt-based","Backbone":"T5"}. This record does not assert independent reproduction. ### GPT-5 F1@5: 11.91. Result ID: 69f8619247f34ce924dc4d39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-5","Prompting Strategy":"Candidate","Zero-shot evaluation":"true"}. This record does not assert independent reproduction. ### Empirical F1@5: 10.97. Result ID: 69f8619247f34ce924dc4d5d. [Reporting paper]() Recorded evaluation configuration: {"Method Type":"Prompt-based","Backbone":"Llama3"}. This record does not assert independent reproduction. ### GPT-5 F1@5: 9.98. Result ID: 69f8619247f34ce924dc4d38. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-5","Prompting Strategy":"Vanilla","Zero-shot evaluation":"true"}. This record does not assert independent reproduction. ### Attention-Seeker F1@5: 8.65. Result ID: 69f8619247f34ce924dc4d5c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Type":"Attention-based","Backbone":"Llama3"}. This record does not assert independent reproduction. ### SAMRank F1@5: 8.16. Result ID: 69f8619247f34ce924dc4d5b. [Reporting paper]() Recorded evaluation configuration: {"Method Type":"Attention-based","Backbone":"Llama3"}. This record does not assert independent reproduction. ### SingleRank F1@5: 7.59. Result ID: 69f8619247f34ce924dc4d55. [Reporting paper]() Recorded evaluation configuration: {"Method Type":"Graph-based"}. This record does not assert independent reproduction. ### TextRank F1@5: 2.91. Result ID: 69f8619247f34ce924dc4d54. [Reporting paper]() Recorded evaluation configuration: {"Method Type":"Graph-based"}. This record does not assert independent reproduction. ### EmbedRank F1@5: 2.35. Result ID: 69f8619247f34ce924dc4d58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Type":"Embedding-based","Backbone":"BERT"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.