# Extreme Multi-label Text Classification on Kan-Shan Cup

Source: [Extreme Multi-label Text Classification on Kan-Shan Cup](<https://www.sota2.com/research/sota/extreme-multi-label-text-classification-on-kan-shan-cup>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:54:44.477Z

Evaluation of Extreme Multi-label Text Classification performance on the Kan-Shan Cup dataset, typically measured using Precision@K and nDCG@K 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 | Extreme Multi-label Text Classification |
| Dataset (including any stated split) | Kan-Shan Cup |
| Metric | P@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [P@1](<https://www.sota2.com/research/sota/extreme-multi-label-text-classification-on-kan-shan-cup.md?metric=P%401>): Higher is better; unit: PERCENT.

- [P@3](<https://www.sota2.com/research/sota/extreme-multi-label-text-classification-on-kan-shan-cup.md?metric=P%403>): Higher is better; unit: PERCENT.

- [P@5](<https://www.sota2.com/research/sota/extreme-multi-label-text-classification-on-kan-shan-cup.md?metric=P%405>): Higher is better; unit: PERCENT.

- [nDCG@3](<https://www.sota2.com/research/sota/extreme-multi-label-text-classification-on-kan-shan-cup.md?metric=nDCG%403>): Higher is better; unit: PERCENT.

- [nDCG@5](<https://www.sota2.com/research/sota/extreme-multi-label-text-classification-on-kan-shan-cup.md?metric=nDCG%405>): Higher is better; unit: PERCENT.

## Recorded results

| Method | P@1 | Result date | Report paper |
| --- | --- | --- | --- |
| LAHA | 54.38 | Not recorded | 68fa65fb1e209131cea0db2e |
| AttentionXML | 53.69 | Not recorded | 68fa65fb1e209131cea0db2e |
| PfastreXML | 52.29 | Not recorded | 68fa65fb1e209131cea0db2e |
| SLEEC | 51.41 | Not recorded | 68fa65fb1e209131cea0db2e |
| XML-CNN | 49.68 | Not recorded | 68fa65fb1e209131cea0db2e |

### LAHA

P@1: 54.38. Result ID: 698cd57d8b517eb4331d0fc2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65fb1e209131cea0db2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fb1e209131cea0db2e.md>)

[Implementation](<https://github.com/HX-idiot/Hybrid_Attention_XML>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AttentionXML

P@1: 53.69. Result ID: 698cd57d8b517eb4331d0fc1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65fb1e209131cea0db2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa669a1e209131cea1155e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PfastreXML

P@1: 52.29. Result ID: 698cd57d8b517eb4331d0fbf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65fb1e209131cea0db2e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SLEEC

P@1: 51.41. Result ID: 698cd57d8b517eb4331d0fbe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65fb1e209131cea0db2e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### XML-CNN

P@1: 49.68. Result ID: 698cd57d8b517eb4331d0fc0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65fb1e209131cea0db2e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
