# Dialogue Quality Evaluation on Persona Sing. Inst.

Source: [Dialogue Quality Evaluation on Persona Sing. Inst.](<https://www.sota2.com/research/sota/dialogue-quality-evaluation-on-persona-sing-inst>)

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

Data updated: 2026-02-26T05:36:44.017Z

Evaluation of dialogue quality using automated metrics such as QuestEval, BF1 variants, Density, and Coverage on the Persona Sing. Inst. dataset.

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 | Dialogue Quality Evaluation |
| Dataset (including any stated split) | Persona Sing. Inst. |
| Metric | BF1 (qt, at) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 1 of 1 |
| 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

- [BF1 (qt, at)](<https://www.sota2.com/research/sota/dialogue-quality-evaluation-on-persona-sing-inst.md?metric=BF1%20(qt%2C%20at)>): Higher is better; unit: SCALAR.

- [QuestEval](<https://www.sota2.com/research/sota/dialogue-quality-evaluation-on-persona-sing-inst.md?metric=QuestEval>): Higher is better; unit: SCALAR.

- [Uptake](<https://www.sota2.com/research/sota/dialogue-quality-evaluation-on-persona-sing-inst.md?metric=Uptake>): Higher is better; unit: SCALAR.

- [1 - Overlap (at, a\<t)](<https://www.sota2.com/research/sota/dialogue-quality-evaluation-on-persona-sing-inst.md?metric=1%20-%20Overlap%20(at%2C%20a%3Ct)>): Lower is better; unit: SCALAR.

- [Density](<https://www.sota2.com/research/sota/dialogue-quality-evaluation-on-persona-sing-inst.md?metric=Density>): Higher is better; unit: SCALAR.

- [Coverage](<https://www.sota2.com/research/sota/dialogue-quality-evaluation-on-persona-sing-inst.md?metric=Coverage>): Higher is better; unit: SCALAR.

- [BF1 (qt, a\<t)](<https://www.sota2.com/research/sota/dialogue-quality-evaluation-on-persona-sing-inst.md?metric=BF1%20(qt%2C%20a%3Ct)>): Higher is better; unit: SCALAR.

- [BF1 (qt, at-1)](<https://www.sota2.com/research/sota/dialogue-quality-evaluation-on-persona-sing-inst.md?metric=BF1%20(qt%2C%20at-1)>): Higher is better; unit: SCALAR.

- [Answerable](<https://www.sota2.com/research/sota/dialogue-quality-evaluation-on-persona-sing-inst.md?metric=Answerable>): Higher is better; unit: SCALAR.

- [QFactScore](<https://www.sota2.com/research/sota/dialogue-quality-evaluation-on-persona-sing-inst.md?metric=QFactScore>): Higher is better; unit: SCALAR.

## Recorded results

| Method | BF1 (qt, at) | Result date | Report paper |
| --- | --- | --- | --- |
| Persona | 0.58 | Not recorded | 68fa72621e209131cea561ac |

### Persona

BF1 (qt, at): 0.58. Result ID: 699235313a6c3148490d51ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72621e209131cea561ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72621e209131cea561ac.md>)

[Implementation](<https://github.com/eth-lre/book2dial>)

Recorded evaluation configuration: {"Configuration":"Single Instruction"}. This record does not assert independent reproduction.

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