# Short Text Clustering on AG News (test) Source: [Short Text Clustering on AG News (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:37.453Z Evaluation of Short Text Clustering performance on the test split of the AG News dataset, measured using Accuracy (Acc.) and Normalized Mutual Information (NMI). 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 | Short Text Clustering | | Dataset (including any stated split) | AG News (test) | | Metric | Accuracy | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [NMI](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Iterative Classification | 86.53 | Not recorded | 68fa692c1e209131cea208b8 | | Iterative Classification | 84.64 | Not recorded | 68fa692c1e209131cea208b8 | | ECIC | 84.52 | Not recorded | 68fa692c1e209131cea208b8 | | Gold | 83.9 | Not recorded | 68fa792f1e209131cea7c7c5 | | k-means | 83.87 | Not recorded | 68fa692c1e209131cea208b8 | | KMeans | 82.7 | Not recorded | 68fa792f1e209131cea7c7c5 | | Gold | 81.3 | Not recorded | 68fa792f1e209131cea7c7c5 | | Gold | 78.9 | Not recorded | 68fa792f1e209131cea7c7c5 | | ZeroDL | 77.6 | Not recorded | 68fa792f1e209131cea7c7c5 | | ZeroDL | 76.6 | Not recorded | 68fa792f1e209131cea7c7c5 | | IDAS | 76.4 | Not recorded | 68fa792f1e209131cea7c7c5 | | ZeroDL | 71.3 | Not recorded | 68fa792f1e209131cea7c7c5 | | IDAS | 68.1 | Not recorded | 68fa792f1e209131cea7c7c5 | | IDAS | 67.7 | Not recorded | 68fa792f1e209131cea7c7c5 | | Gold | 64.1 | Not recorded | 68fa792f1e209131cea7c7c5 | | IDAS | 55.4 | Not recorded | 68fa792f1e209131cea7c7c5 | | ZeroDL | 54.5 | Not recorded | 68fa792f1e209131cea7c7c5 | | KMeans | 43.8 | Not recorded | 68fa792f1e209131cea7c7c5 | ### Iterative Classification Accuracy: 86.53. Result ID: 698d9b618b517eb43322a289. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier":"Logistic Regression","Clustering Stage":"Iterative"}. This record does not assert independent reproduction. ### Iterative Classification Accuracy: 84.64. Result ID: 698d9b618b517eb43322a288. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier":"RoBERTa","Clustering Stage":"Iterative"}. This record does not assert independent reproduction. ### ECIC Accuracy: 84.52. Result ID: 698d9b618b517eb43322a286. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Description":"Ensemble Clustering with Transformers"}. This record does not assert independent reproduction. ### Gold Accuracy: 83.9. Result ID: 6995cf833badfaffe6d450e2. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen-2.5-72b-it","Prompt Order":"T-C"}. This record does not assert independent reproduction. ### k-means Accuracy: 83.87. Result ID: 698d9b618b517eb43322a287. [Reporting paper]() Recorded evaluation configuration: {"Clustering Stage":"Initial"}. This record does not assert independent reproduction. ### KMeans Accuracy: 82.7. Result ID: 6995cf833badfaffe6d450d6. [Reporting paper]() Recorded evaluation configuration: {"Model":"SBERT"}. This record does not assert independent reproduction. ### Gold Accuracy: 81.3. Result ID: 6995cf833badfaffe6d450df. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen-2.5-72b-it","Prompt Order":"C-T"}. This record does not assert independent reproduction. ### Gold Accuracy: 78.9. Result ID: 6995cf833badfaffe6d450dc. [Reporting paper]() Recorded evaluation configuration: {"Model":"llama-3.1-8b-it","Prompt Order":"T-C"}. This record does not assert independent reproduction. ### ZeroDL Accuracy: 77.6. Result ID: 6995cf833badfaffe6d450da. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"llama-3.1-8b-it","Prompt Order":"T-C"}. This record does not assert independent reproduction. ### ZeroDL Accuracy: 76.6. Result ID: 6995cf833badfaffe6d450e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen-2.5-72b-it","Prompt Order":"T-C"}. This record does not assert independent reproduction. ### IDAS Accuracy: 76.4. Result ID: 6995cf833badfaffe6d450e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen-2.5-72b-it","Prompt Order":"T-C"}. This record does not assert independent reproduction. ### ZeroDL Accuracy: 71.3. Result ID: 6995cf833badfaffe6d450dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen-2.5-72b-it","Prompt Order":"C-T"}. This record does not assert independent reproduction. ### IDAS Accuracy: 68.1. Result ID: 6995cf833badfaffe6d450de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen-2.5-72b-it","Prompt Order":"C-T"}. This record does not assert independent reproduction. ### IDAS Accuracy: 67.7. Result ID: 6995cf833badfaffe6d450db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"llama-3.1-8b-it","Prompt Order":"T-C"}. This record does not assert independent reproduction. ### Gold Accuracy: 64.1. Result ID: 6995cf833badfaffe6d450d9. [Reporting paper]() Recorded evaluation configuration: {"Model":"llama-3.1-8b-it","Prompt Order":"C-T"}. This record does not assert independent reproduction. ### IDAS Accuracy: 55.4. Result ID: 6995cf833badfaffe6d450d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"llama-3.1-8b-it","Prompt Order":"C-T"}. This record does not assert independent reproduction. ### ZeroDL Accuracy: 54.5. Result ID: 6995cf833badfaffe6d450d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"llama-3.1-8b-it","Prompt Order":"C-T"}. This record does not assert independent reproduction. ### KMeans Accuracy: 43.8. Result ID: 6995cf833badfaffe6d450d5. [Reporting paper]() Recorded evaluation configuration: {"Model":"TF-IDF"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.