# Human Preference Evaluation for Code-switched Text Generation on In-Domain Data Source: [Human Preference Evaluation for Code-switched Text Generation on In-Domain Data]() Collection index: [llms.txt]() Data updated: 2026-03-09T06:39:14.391Z Human preference evaluation assessing model performance on code-switched text generation using the English-to-Code-Switched In-Domain dataset, measured via direct scoring and ranking. 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 (In domain) | | Metric | Preference Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Preference Score](): Higher is better; unit: SCALAR. - [Preference Rank](): Lower is better; unit: SCALAR. ## Recorded results | Method | Preference Score | Result date | Report paper | | --- | --- | --- | --- | | Gold Standard | 804 | Not recorded | 68fa78c51e209131cea7a6a5 | | Llama3 | 573.5 | Not recorded | 68fa78c51e209131cea7a6a5 | | NLLB | 507 | Not recorded | 68fa78c51e209131cea7a6a5 | | Llama3 Instruct | 480.5 | Not recorded | 68fa78c51e209131cea7a6a5 | | GPT-4ofs | 413.5 | Not recorded | 68fa78c51e209131cea7a6a5 | | Llama3.3-70Bfs | 371.5 | Not recorded | 68fa78c51e209131cea7a6a5 | | Gold Standard | 369.5 | Not recorded | 68fa78c51e209131cea7a6a5 | | Llama3 | 291.5 | Not recorded | 68fa78c51e209131cea7a6a5 | | Llama3 Instruct | 270.5 | Not recorded | 68fa78c51e209131cea7a6a5 | | NLLB | 259.5 | Not recorded | 68fa78c51e209131cea7a6a5 | | GPT-4ofs | 251.5 | Not recorded | 68fa78c51e209131cea7a6a5 | | Llama3.3-70Bfs | 207.5 | Not recorded | 68fa78c51e209131cea7a6a5 | ### Gold Standard Preference Score: 804. Result ID: 69ae6aaa6dbb7075b955d9a6. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Llama3 Preference Score: 573.5. Result ID: 69ae6aaa6dbb7075b955d9a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training":"fine-tuned"}. This record does not assert independent reproduction. ### NLLB Preference Score: 507. Result ID: 69ae6aaa6dbb7075b955d9a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training":"fine-tuned","backbone":"nllb-200-distilled-600M"}. This record does not assert independent reproduction. ### Llama3 Instruct Preference Score: 480.5. Result ID: 69ae6aaa6dbb7075b955d9a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training":"fine-tuned"}. This record does not assert independent reproduction. ### GPT-4ofs Preference Score: 413.5. Result ID: 69ae6aaa6dbb7075b955d9aa. [Reporting paper]() Recorded evaluation configuration: {"mode":"5-shot"}. This record does not assert independent reproduction. ### Llama3.3-70Bfs Preference Score: 371.5. Result ID: 69ae6aaa6dbb7075b955d9ab. [Reporting paper]() Recorded evaluation configuration: {"mode":"5-shot"}. This record does not assert independent reproduction. ### Gold Standard Preference Score: 369.5. Result ID: 69ae6aaa6dbb7075b955d99a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Llama3 Preference Score: 291.5. Result ID: 69ae6aaa6dbb7075b955d99b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training":"fine-tuned"}. This record does not assert independent reproduction. ### Llama3 Instruct Preference Score: 270.5. Result ID: 69ae6aaa6dbb7075b955d99c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training":"fine-tuned"}. This record does not assert independent reproduction. ### NLLB Preference Score: 259.5. Result ID: 69ae6aaa6dbb7075b955d99d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training":"fine-tuned","backbone":"nllb-200-distilled-600M"}. This record does not assert independent reproduction. ### GPT-4ofs Preference Score: 251.5. Result ID: 69ae6aaa6dbb7075b955d99e. [Reporting paper]() Recorded evaluation configuration: {"mode":"5-shot"}. This record does not assert independent reproduction. ### Llama3.3-70Bfs Preference Score: 207.5. Result ID: 69ae6aaa6dbb7075b955d99f. [Reporting paper]() 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.