Fact-Checking on LIAR (test)
68.2AccuracyUPA
Evaluation Results
| Method | Links | |
|---|---|---|
| UPAVenue=-, Execution Engine=GPT-4o-mini2026.01 | 68.2 | |
| OPROVenue=ICLR 24, Execution Engine=GPT-4o-mini2026.01 | 67.6 | |
| SPOVenue=EMNLP 26, Execution Engine=GPT-4o-mini2026.01 | 66.9 | |
| APEVenue=ICLR 23, Execution Engine=GPT-4o-mini2026.01 | 65.9 | |
| TextGradVenue=Nature 25, Execution Engine=GPT-4o-mini2026.01 | 65.7 | |
| CoTVenue=NeurIPS 22, Execution Engine=GPT-4o-mini2026.01 | 65.4 | |
| PromptAgentVenue=ICLR 24, Execution Engine=GPT-4o-mini2026.01 | 64.1 | |
| IOVenue=-, Execution Engine=GPT-4o-mini2026.01 | 63.5 | |
| PromptBreederVenue=ICML 24, Execution Engine=GPT-4o-mini2026.01 | 63.2 | |
| Step-BackVenue=ICLR 24, Execution Engine=GPT-4o-mini2026.01 | 62.8 | |
| RaRVenue=arXiv 23, Execution Engine=GPT-4o-mini2026.01 | 50.5 |