# Clustering on ArxivS2S

Source: [Clustering on ArxivS2S](<https://www.sota2.com/research/sota/clustering-on-arxivs2s>)

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

Data updated: 2026-04-08T09:15:48.640Z

Evaluation of unsupervised clustering performance on the ArxivS2S dataset, reporting Accuracy (ACC), Normalized Mutual Information (NMI), and Adjusted Rand Index (ARI).

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 | Clustering |
| Dataset (including any stated split) | ArxivS2S |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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](<https://www.sota2.com/research/sota/clustering-on-arxivs2s.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Normalized Mutual Information](<https://www.sota2.com/research/sota/clustering-on-arxivs2s.md?metric=Normalized%20Mutual%20Information>): Higher is better; unit: PERCENT.

- [Adjusted Rand Index](<https://www.sota2.com/research/sota/clustering-on-arxivs2s.md?metric=Adjusted%20Rand%20Index>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LLM-MemCluster | 28.4 | Not recorded | 691ea080d6b0dd334292df4c |
| Spectral | 25.1 | Not recorded | 691ea080d6b0dd334292df4c |
| K-Means-Inst | 25.1 | Not recorded | 691ea080d6b0dd334292df4c |
| ClusterLLM | 25.1 | Not recorded | 691ea080d6b0dd334292df4c |
| BERTopic | 17.9 | Not recorded | 691ea080d6b0dd334292df4c |
| K-Means-TF-IDF | 12.1 | Not recorded | 691ea080d6b0dd334292df4c |
| DBSCAN | 6.3 | Not recorded | 691ea080d6b0dd334292df4c |

### LLM-MemCluster

Accuracy: 28.4. Result ID: 69d61cb347f34ce924bee8e7.

[Reporting paper](<https://www.sota2.com/research/paper/691ea080d6b0dd334292df4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691ea080d6b0dd334292df4c.md>)

Recorded evaluation configuration: {"In-context learning":"true","Model":"GPT-4.1 mini"}. This record does not assert independent reproduction.

### Spectral

Accuracy: 25.1. Result ID: 69d61cb347f34ce924bee8e3.

[Reporting paper](<https://www.sota2.com/research/paper/691ea080d6b0dd334292df4c.md>)

Recorded evaluation configuration: {"Embeddings":"instructor-large"}. This record does not assert independent reproduction.

### K-Means-Inst

Accuracy: 25.1. Result ID: 69d61cb347f34ce924bee8e5.

[Reporting paper](<https://www.sota2.com/research/paper/691ea080d6b0dd334292df4c.md>)

Recorded evaluation configuration: {"Embeddings":"instructor-large"}. This record does not assert independent reproduction.

### ClusterLLM

Accuracy: 25.1. Result ID: 69d61cb347f34ce924bee8e6.

[Reporting paper](<https://www.sota2.com/research/paper/691ea080d6b0dd334292df4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710f1e209131cea4ef3d.md>)

Recorded evaluation configuration: {"Embeddings":"instructor-large","Guidance Model":"GPT-4.1 mini"}. This record does not assert independent reproduction.

### BERTopic

Accuracy: 17.9. Result ID: 69d61cb347f34ce924bee8e4.

[Reporting paper](<https://www.sota2.com/research/paper/691ea080d6b0dd334292df4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfd1e209131cea31795.md>)

Recorded evaluation configuration: {"Embeddings":"instructor-large"}. This record does not assert independent reproduction.

### K-Means-TF-IDF

Accuracy: 12.1. Result ID: 69d61cb247f34ce924bee8e1.

[Reporting paper](<https://www.sota2.com/research/paper/691ea080d6b0dd334292df4c.md>)

Recorded evaluation configuration: {"Embeddings":"TF-IDF"}. This record does not assert independent reproduction.

### DBSCAN

Accuracy: 6.3. Result ID: 69d61cb347f34ce924bee8e2.

[Reporting paper](<https://www.sota2.com/research/paper/691ea080d6b0dd334292df4c.md>)

Recorded evaluation configuration: {"Embeddings":"instructor-large"}. This record does not assert independent reproduction.

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