# Dynamic Aspect-Based Summarization on D-WikiHow (test)

Source: [Dynamic Aspect-Based Summarization on D-WikiHow (test)](<https://www.sota2.com/research/sota/dynamic-aspect-based-summarization-on-d-wikihow-test>)

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

Data updated: 2026-02-26T05:21:22.228Z

Evaluation of Dynamic Aspect-Based Summarization performance on the test split of the D-WikiHow dataset, utilizing metrics such as ROUGE scores, BERTScore, and the custom #AbsAspDiff metric.

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 | Dynamic Aspect-Based Summarization |
| Dataset (including any stated split) | D-WikiHow (test) |
| Metric | #AbsAspDiff |
| Unit | SCALAR |
| 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

- [#AbsAspDiff](<https://www.sota2.com/research/sota/dynamic-aspect-based-summarization-on-d-wikihow-test.md?metric=%23AbsAspDiff>): Higher is better; unit: SCALAR.

- [BERTScore](<https://www.sota2.com/research/sota/dynamic-aspect-based-summarization-on-d-wikihow-test.md?metric=BERTScore>): Higher is better; unit: PERCENT.

- [ROUGE-1](<https://www.sota2.com/research/sota/dynamic-aspect-based-summarization-on-d-wikihow-test.md?metric=ROUGE-1>): Higher is better; unit: PERCENT.

- [ROUGE-2](<https://www.sota2.com/research/sota/dynamic-aspect-based-summarization-on-d-wikihow-test.md?metric=ROUGE-2>): Higher is better; unit: PERCENT.

- [ROUGE-L](<https://www.sota2.com/research/sota/dynamic-aspect-based-summarization-on-d-wikihow-test.md?metric=ROUGE-L>): Higher is better; unit: PERCENT.

## Recorded results

| Method | #AbsAspDiff | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-3.5-Zero | 5.5 | Not recorded | 68fa73a91e209131cea5dbd4 |
| GPT-3.5-Tuned | 3.8 | Not recorded | 68fa73a91e209131cea5dbd4 |
| Keywords | 2.7 | Not recorded | 68fa73a91e209131cea5dbd4 |
| Cluster | 2.7 | Not recorded | 68fa73a91e209131cea5dbd4 |
| MODABS | 1.5 | Not recorded | 68fa73a91e209131cea5dbd4 |

### GPT-3.5-Zero

#AbsAspDiff: 5.5. Result ID: 6993070a3a6c314849132a05.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a91e209131cea5dbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5db98.md>)

Recorded evaluation configuration: {"mode":"zero-shot"}. This record does not assert independent reproduction.

### GPT-3.5-Tuned

#AbsAspDiff: 3.8. Result ID: 6993070a3a6c314849132a06.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a91e209131cea5dbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5db98.md>)

Recorded evaluation configuration: {"mode":"fine-tuned"}. This record does not assert independent reproduction.

### Keywords

#AbsAspDiff: 2.7. Result ID: 6993070a3a6c314849132a03.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a91e209131cea5dbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5db98.md>)

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

### Cluster

#AbsAspDiff: 2.7. Result ID: 6993070a3a6c314849132a04.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a91e209131cea5dbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a81e209131cea5db98.md>)

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

### MODABS

#AbsAspDiff: 1.5. Result ID: 6993070a3a6c314849132a07.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a91e209131cea5dbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a91e209131cea5dbd4.md>)

[Implementation](<https://github.com/xiaobo-guo/MODABS>)

Recorded evaluation configuration: {"backbone":"Longformer-Encoder-Decoder"}. This record does not assert independent reproduction.

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