Cross-lingual Question Answering on Open-Ended CLQA
325Rank 1 CountLlama_CL
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Llama_CLEvaluation protocol=1-4 scale rating, Evaluation judge=Claude 3.5, Total samples=1,0002026.04 | 325 | 190 | 202 | 220 | 63 | |
| L_NTPEvaluation protocol=1-4 scale rating, Evaluation judge=Claude 3.5, Total samples=1,0002026.04 | 271 | 182 | 213 | 271 | 63 | |
| L_Bi_NTPEvaluation protocol=1-4 scale rating, Evaluation judge=Claude 3.5, Total samples=1,0002026.04 | 252 | 281 | 212 | 192 | 63 | |
| L-3-8BEvaluation protocol=1-4 scale rating, Evaluation judge=Claude 3.5, Total samples=1,0002026.04 | 181 | 332 | 261 | 163 | 63 |