# Faithfulness Evaluation on SummEval

Source: [Faithfulness Evaluation on SummEval](<https://www.sota2.com/research/sota/faithfulness-evaluation-on-summeval>)

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

Data updated: 2026-04-13T07:41:30.334Z

Evaluation of model faithfulness using the SummEval dataset, measured by Kendall's tau (τ) and Mean Absolute Error (MAE).

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 | Faithfulness Evaluation |
| Dataset (including any stated split) | SummEval |
| Metric | Kendall's tau (τ) |
| 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

- [Kendall's tau (τ)](<https://www.sota2.com/research/sota/faithfulness-evaluation-on-summeval.md?metric=Kendall%27s%20tau%20(%CF%84)>): Higher is better; unit: SCALAR.

- [MAE](<https://www.sota2.com/research/sota/faithfulness-evaluation-on-summeval.md?metric=MAE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Kendall's tau (τ) | Result date | Report paper |
| --- | --- | --- | --- |
| RAGAS | 0.535 | Not recorded | 69dc788a7d0172140ec78aa8 |
| TCVA | 0.527 | Not recorded | 69dc788a7d0172140ec78aa8 |
| DeepEval | 0.302 | Not recorded | 69dc788a7d0172140ec78aa8 |

### RAGAS

Kendall's tau (τ): 0.535. Result ID: 69dc9e1a47f34ce924c35070.

[Reporting paper](<https://www.sota2.com/research/paper/69dc788a7d0172140ec78aa8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78451e209131cea7784e.md>)

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

### TCVA

Kendall's tau (τ): 0.527. Result ID: 69dc9e1a47f34ce924c3506f.

[Reporting paper](<https://www.sota2.com/research/paper/69dc788a7d0172140ec78aa8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc788a7d0172140ec78aa8.md>)

Recorded evaluation configuration: {"Temperature (T)":"best T"}. This record does not assert independent reproduction.

### DeepEval

Kendall's tau (τ): 0.302. Result ID: 69dc9e1a47f34ce924c35071.

[Reporting paper](<https://www.sota2.com/research/paper/69dc788a7d0172140ec78aa8.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.