Open QA Evaluation on EVOUNA-TriviaQA
100F1 ScoreAnother Human
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Another HumanQA System=DPR-FiD2024.05 | 100 | 100 | |
| Another HumanQA System=BingChat2024.05 | 99.9 | 95.5 | |
| Another HumanQA System=InstructGPT2024.05 | 99.6 | 99.4 | |
| Another HumanQA System=ChatGPT2024.05 | 99.2 | 98.8 | |
| Another HumanQA System=GPT-42024.05 | 99.2 | 99.8 | |
| EntailmentQA System=GPT-42024.05 | 97.4 | 95.3 | |
| GPT-3.5QA System=DPR-FiD2024.05 | 97.3 | 95.7 | |
| EntailmentQA System=DPR-FiD2024.05 | 96.8 | 94.7 | |
| EntailmentQA System=InstructGPT2024.05 | 96.6 | 94.2 | |
| EntailmentQA System=ChatGPT2024.05 | 96.6 | 94.2 | |
| EntailmentQA System=BingChat2024.05 | 95.9 | 92.5 | |
| GPT-3.5QA System=GPT-42024.05 | 95.7 | 92.4 | |
| GPT-3.5QA System=ChatGPT2024.05 | 95.5 | 92.5 | |
| Lexical MatchQA System=ChatGPT2024.05 | 95.2 | 92.3 | |
| Lexical MatchQA System=InstructGPT2024.05 | 94.8 | 92.3 | |
| Lexical MatchQA System=GPT-42024.05 | 94.8 | 91.1 | |
| GPT-3.5QA System=InstructGPT2024.05 | 94.2 | 91.2 | |
| Lexical MatchQA System=BingChat2024.05 | 94.1 | 89.8 | |
| Lexical MatchQA System=DPR-FiD2024.05 | 91.8 | 94.7 | |
| BERTScoreQA System=GPT-42024.05 | 90.5 | 93.5 | |
| BERTScoreQA System=ChatGPT2024.05 | 88.4 | 80.8 | |
| BERTScoreQA System=BingChat2024.05 | 88.3 | 80.4 | |
| GPT-3.5QA System=BingChat2024.05 | 88.2 | 80.9 | |
| BERTScoreQA System=InstructGPT2024.05 | 84.1 | 75.7 | |
| BERTScoreQA System=DPR-FiD2024.05 | 75.1 | 65.5 |