# Semantic Similarity on Simulated Music Recommendation Conversations

Source: [Semantic Similarity on Simulated Music Recommendation Conversations](<https://www.sota2.com/research/sota/semantic-similarity-on-simulated-music-recommendation-conversations>)

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

Data updated: 2026-02-26T05:37:44.032Z

Evaluation of Semantic Similarity performance on the Simulated Music Recommendation Conversations dataset, utilizing metrics such as BertScore, AB Divergence, L2 Distance, and Fisher-Rao Distance.

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 | Semantic Similarity |
| Dataset (including any stated split) | Simulated Music Recommendation Conversations |
| Metric | BertScore F1 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [BertScore F1](<https://www.sota2.com/research/sota/semantic-similarity-on-simulated-music-recommendation-conversations.md?metric=BertScore%20F1>): Higher is better; unit: SCALAR.

- [AB Divergence](<https://www.sota2.com/research/sota/semantic-similarity-on-simulated-music-recommendation-conversations.md?metric=AB%20Divergence>): Lower is better; unit: SCALAR.

- [L2 Distance](<https://www.sota2.com/research/sota/semantic-similarity-on-simulated-music-recommendation-conversations.md?metric=L2%20Distance>): Lower is better; unit: SCALAR.

- [Fisher-Rao Distance](<https://www.sota2.com/research/sota/semantic-similarity-on-simulated-music-recommendation-conversations.md?metric=Fisher-Rao%20Distance>): Lower is better; unit: SCALAR.

## Recorded results

| Method | BertScore F1 | Result date | Report paper |
| --- | --- | --- | --- |
| MuseChat | 0.9676 | Not recorded | 68fa72711e209131cea5659e |
| Vicuna w/ Music | 0.9526 | Not recorded | 68fa72711e209131cea5659e |
| Vicuna-7B | 0.9453 | Not recorded | 68fa72711e209131cea5659e |

### MuseChat

BertScore F1: 0.9676. Result ID: 699238fe3a6c3148490d6c28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72711e209131cea5659e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea5659e.md>)

Recorded evaluation configuration: {"Input Modality":"Music Title + Embeddings"}. This record does not assert independent reproduction.

### Vicuna w/ Music

BertScore F1: 0.9526. Result ID: 699238fe3a6c3148490d6c27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72711e209131cea5659e.md>)

Recorded evaluation configuration: {"Input Modality":"Music Embeddings"}. This record does not assert independent reproduction.

### Vicuna-7B

BertScore F1: 0.9453. Result ID: 699238fe3a6c3148490d6c26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72711e209131cea5659e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71aa1e209131cea526df.md>)

[Implementation](<https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge>)

Recorded evaluation configuration: {"Input Modality":"Music Title"}. This record does not assert independent reproduction.

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