# Trustworthiness Evaluation on Adv Fact (human evaluation)

Source: [Trustworthiness Evaluation on Adv Fact (human evaluation)](<https://www.sota2.com/research/sota/trustworthiness-evaluation-on-adv-fact-human-evaluation>)

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

Data updated: 2026-02-26T05:39:50.287Z

Human evaluation results assessing model trustworthiness on the Adv Fact dataset, categorized by wins, ties, and non-control wins against a control model.

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 | Trustworthiness Evaluation |
| Dataset (including any stated split) | Adv Fact (human evaluation) |
| Metric | Control Wins |
| 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

- [Control Wins](<https://www.sota2.com/research/sota/trustworthiness-evaluation-on-adv-fact-human-evaluation.md?metric=Control%20Wins>): Higher is better; unit: SCALAR.

- [Tie Count](<https://www.sota2.com/research/sota/trustworthiness-evaluation-on-adv-fact-human-evaluation.md?metric=Tie%20Count>): Higher is better; unit: SCALAR.

- [No Control Wins](<https://www.sota2.com/research/sota/trustworthiness-evaluation-on-adv-fact-human-evaluation.md?metric=No%20Control%20Wins>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Control Wins | Result date | Report paper |
| --- | --- | --- | --- |
| Sparse Activation Control | 68 | Not recorded | 68fa75891e209131cea68742 |

### Sparse Activation Control

Control Wins: 68. Result ID: 6993cfec3a6c31484918b8f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75891e209131cea68742.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75891e209131cea68742.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.
