# Human Preference Evaluation for Code-switched Text Generation on EN-CS (Out of domain)

Source: [Human Preference Evaluation for Code-switched Text Generation on EN-CS (Out of domain)](<https://www.sota2.com/research/sota/human-preference-evaluation-for-code-switched-text-generation-on-en-cs-out-of-domain>)

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

Data updated: 2026-03-09T06:39:14.425Z

Human preference evaluation assessing model output quality for code-switched text generation using out-of-domain samples, measured via direct Score and Rank.

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 | Code-switched text generation |
| Dataset (including any stated split) | English-to-Code-Switched human preference evaluation (Out of domain) |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Score](<https://www.sota2.com/research/sota/human-preference-evaluation-for-code-switched-text-generation-on-en-cs-out-of-domain.md?metric=Score>): Higher is better; unit: SCALAR.

- [Rank](<https://www.sota2.com/research/sota/human-preference-evaluation-for-code-switched-text-generation-on-en-cs-out-of-domain.md?metric=Rank>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| Gold Standard | 434.5 | Not recorded | 68fa78c51e209131cea7a6a5 |
| Llama3 | 282 | Not recorded | 68fa78c51e209131cea7a6a5 |
| NLLB | 247.5 | Not recorded | 68fa78c51e209131cea7a6a5 |
| Llama3 Instruct | 210 | Not recorded | 68fa78c51e209131cea7a6a5 |
| Llama3.3-70Bfs | 164 | Not recorded | 68fa78c51e209131cea7a6a5 |
| GPT-4ofs | 162 | Not recorded | 68fa78c51e209131cea7a6a5 |

### Gold Standard

Score: 434.5. Result ID: 69ae6aaa6dbb7075b955d9a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a6a5.md>)

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

### Llama3

Score: 282. Result ID: 69ae6aaa6dbb7075b955d9a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a6a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a6a5.md>)

Recorded evaluation configuration: {"training":"fine-tuned"}. This record does not assert independent reproduction.

### NLLB

Score: 247.5. Result ID: 69ae6aaa6dbb7075b955d9a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a6a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a6a5.md>)

Recorded evaluation configuration: {"training":"fine-tuned","backbone":"nllb-200-distilled-600M"}. This record does not assert independent reproduction.

### Llama3 Instruct

Score: 210. Result ID: 69ae6aaa6dbb7075b955d9a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a6a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a6a5.md>)

Recorded evaluation configuration: {"training":"fine-tuned"}. This record does not assert independent reproduction.

### Llama3.3-70Bfs

Score: 164. Result ID: 69ae6aaa6dbb7075b955d9a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a6a5.md>)

Recorded evaluation configuration: {"mode":"5-shot"}. This record does not assert independent reproduction.

### GPT-4ofs

Score: 162. Result ID: 69ae6aaa6dbb7075b955d9a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a6a5.md>)

Recorded evaluation configuration: {"mode":"5-shot"}. This record does not assert independent reproduction.

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