# PRP Faithfulness Evaluation on Alice original characters 8 persona statements

Source: [PRP Faithfulness Evaluation on Alice original characters 8 persona statements](<https://www.sota2.com/research/sota/prp-faithfulness-evaluation-on-alice-original-characters-8-persona-statements>)

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

Data updated: 2026-02-26T06:11:24.473Z

Evaluation of model faithfulness concerning PRP (Persona Reference Preservation) using the Alice original characters 8 persona statements dataset, measured by ΔAPC (DeB), ΔAPC (GPT-4), and Human evaluation scores.

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 | PRP Faithfulness Evaluation |
| Dataset (including any stated split) | Alice original characters 8 persona statements |
| Metric | ΔAPC (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

- [ΔAPC (DeB)](<https://www.sota2.com/research/sota/prp-faithfulness-evaluation-on-alice-original-characters-8-persona-statements.md?metric=%CE%94APC%20(DeB)>): Higher is better; unit: SCALAR.

- [ΔAPC (GPT-4)](<https://www.sota2.com/research/sota/prp-faithfulness-evaluation-on-alice-original-characters-8-persona-statements.md?metric=%CE%94APC%20(GPT-4)>): Higher is better; unit: SCALAR.

- [Human Score](<https://www.sota2.com/research/sota/prp-faithfulness-evaluation-on-alice-original-characters-8-persona-statements.md?metric=Human%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | ΔAPC (DeB) | Result date | Report paper |
| --- | --- | --- | --- |
| Retrieval-augmented Generation (RAG) | 2.9 | Not recorded | 68fa753e1e209131cea66b68 |
| Retrieval-augmented Generation (RAG) | 2.8 | Not recorded | 68fa753e1e209131cea66b68 |
| Long-context Memory (LCM) | 2.8 | Not recorded | 68fa753e1e209131cea66b68 |
| Experience Upload (EU) | 2.7 | Not recorded | 68fa753e1e209131cea66b68 |
| Experience Upload (EU) | 2.6 | Not recorded | 68fa753e1e209131cea66b68 |
| Long-context Memory (LCM) | 2.6 | Not recorded | 68fa753e1e209131cea66b68 |
| Gemma-7B | 0.7 | Not recorded | 68fa753e1e209131cea66b68 |

### Retrieval-augmented Generation (RAG)

ΔAPC (DeB): 2.9. Result ID: 699397123a6c31484917165c.

[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 (APC-based DPO)":"True"}. This record does not assert independent reproduction.

### Retrieval-augmented Generation (RAG)

ΔAPC (DeB): 2.8. Result ID: 699397123a6c314849171659.

[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 (APC-based DPO)":"False"}. This record does not assert independent reproduction.

### Long-context Memory (LCM)

ΔAPC (DeB): 2.8. Result ID: 699397123a6c31484917165b.

[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 (APC-based DPO)":"True"}. This record does not assert independent reproduction.

### Experience Upload (EU)

ΔAPC (DeB): 2.7. Result ID: 699397123a6c31484917165a.

[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 (APC-based DPO)":"True"}. This record does not assert independent reproduction.

### Experience Upload (EU)

ΔAPC (DeB): 2.6. Result ID: 699397123a6c314849171657.

[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 (APC-based DPO)":"False"}. This record does not assert independent reproduction.

### Long-context Memory (LCM)

ΔAPC (DeB): 2.6. Result ID: 699397123a6c314849171658.

[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 (APC-based DPO)":"False"}. This record does not assert independent reproduction.

### Gemma-7B

ΔAPC (DeB): 0.7. Result ID: 699397123a6c314849171656.

[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 (APC-based DPO)":"False"}. This record does not assert independent reproduction.

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