# PRP Faithfulness Evaluation on Simple and contamination-free characters Alice 8 statements (test v1.0)

Source: [PRP Faithfulness Evaluation on Simple and contamination-free characters Alice 8 statements (test v1.0)](<https://www.sota2.com/research/sota/prp-faithfulness-evaluation-on-simple-and-contamination-free-characters-alice-8-statements-test-v1-0>)

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

Data updated: 2026-02-26T05:23:26.613Z

Evaluation of model faithfulness for Persona Role-Playing (PRP) using the specific test split (v1.0) of the 'Simple and contamination-free characters Alice, 8 statements' dataset. Metrics include APC scores derived from DeB and GPT-4 evaluations, alongside Human assessment.

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 | Persona Role-Playing Faithfulness |
| Dataset (including any stated split) | Simple and contamination-free characters Alice, 8 statements 1.0 (test) |
| Metric | APC (DeB) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [APC (DeB)](<https://www.sota2.com/research/sota/prp-faithfulness-evaluation-on-simple-and-contamination-free-characters-alice-8-statements-test-v1-0.md?metric=APC%20(DeB)>): Higher is better; unit: SCALAR.

- [APC (GPT-4)](<https://www.sota2.com/research/sota/prp-faithfulness-evaluation-on-simple-and-contamination-free-characters-alice-8-statements-test-v1-0.md?metric=APC%20(GPT-4)>): Higher is better; unit: SCALAR.

- [Human Assessment Score](<https://www.sota2.com/research/sota/prp-faithfulness-evaluation-on-simple-and-contamination-free-characters-alice-8-statements-test-v1-0.md?metric=Human%20Assessment%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | APC (DeB) | Result date | Report paper |
| --- | --- | --- | --- |
| RAG | 6.5 | Not recorded | 68fa753e1e209131cea66b68 |
| RAG | 6.4 | Not recorded | 68fa753e1e209131cea66b68 |
| LCM | 6.4 | Not recorded | 68fa753e1e209131cea66b68 |
| EU | 6.3 | Not recorded | 68fa753e1e209131cea66b68 |
| EU | 6.2 | Not recorded | 68fa753e1e209131cea66b68 |
| LCM | 6.2 | Not recorded | 68fa753e1e209131cea66b68 |
| Gemma-7B | 4.3 | Not recorded | 68fa753e1e209131cea66b68 |

### RAG

APC (DeB): 6.5. Result ID: 699397123a6c314849171671.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Implementation](<https://github.com/KomeijiForce/Active_Passive_Constraint_Koishiday_2024>)

Recorded evaluation configuration: {"CPO Status":"With CPO"}. This record does not assert independent reproduction.

### RAG

APC (DeB): 6.4. Result ID: 699397123a6c31484917166e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Implementation](<https://github.com/KomeijiForce/Active_Passive_Constraint_Koishiday_2024>)

Recorded evaluation configuration: {"CPO Status":"Without CPO"}. This record does not assert independent reproduction.

### LCM

APC (DeB): 6.4. Result ID: 699397123a6c314849171670.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Implementation](<https://github.com/KomeijiForce/Active_Passive_Constraint_Koishiday_2024>)

Recorded evaluation configuration: {"CPO Status":"With CPO"}. This record does not assert independent reproduction.

### EU

APC (DeB): 6.3. Result ID: 699397123a6c31484917166f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Implementation](<https://github.com/KomeijiForce/Active_Passive_Constraint_Koishiday_2024>)

Recorded evaluation configuration: {"CPO Status":"With CPO"}. This record does not assert independent reproduction.

### EU

APC (DeB): 6.2. Result ID: 699397123a6c31484917166c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Implementation](<https://github.com/KomeijiForce/Active_Passive_Constraint_Koishiday_2024>)

Recorded evaluation configuration: {"CPO Status":"Without CPO"}. This record does not assert independent reproduction.

### LCM

APC (DeB): 6.2. Result ID: 699397123a6c31484917166d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Implementation](<https://github.com/KomeijiForce/Active_Passive_Constraint_Koishiday_2024>)

Recorded evaluation configuration: {"CPO Status":"Without CPO"}. This record does not assert independent reproduction.

### Gemma-7B

APC (DeB): 4.3. Result ID: 699397123a6c31484917166b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b68.md>)

[Implementation](<https://github.com/KomeijiForce/Active_Passive_Constraint_Koishiday_2024>)

Recorded evaluation configuration: {"CPO Status":"Without CPO"}. This record does not assert independent reproduction.

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