Claim Correction on SciFact Gold evidence
42.6331SARIM2C
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| M2CLLM=Qwen-2.5 (32B), Masking=Diversity-aware (DM)2026.04 | 42.6331 | -2.1453 | |
| M2C+LLM=Qwen-2.5 (32B), Masking=Diversity-aware (DM)2026.04 | 42.6331 | -2.1453 | |
| M2Cw/VerLLM=Qwen-2.5 (32B), Ranker=MonoT52026.04 | 42.6284 | -2.6048 | |
| M2CLLM=Llama-2.0 (70B), Masking=Diversity-aware (DM)2026.04 | 40.0456 | -2.6892 | |
| M2C+LLM=Llama-2.0 (70B), Masking=Diversity-aware (DM)2026.04 | 40.0456 | -2.6892 | |
| RAGLLM=Llama-2.0 (70B), Ranker=MonoT52026.04 | 36.5339 | -2.3658 | |
| RAGLLM=Qwen-2.5 (32B), Ranker=MonoT52026.04 | 34.778 | -2.8676 | |
| ZeroFeC-DALLM=n/a, Predictor=ZeroFeC-DA, Ranker=MonoT52026.04 | 32.1988 | -3.1756 | |
| M2Cw/VerLLM=Llama-2.0 (70B), Ranker=MonoT52026.04 | 30.6697 | -3.1277 | |
| COMPEDITLLM=n/a, Predictor=COMPEDIT, Ranker=MonoT52026.04 | 30.6196 | -3.0591 | |
| T5-DistantLLM=n/a, Predictor=T5-Distant, Ranker=GENRE2026.04 | 22.9304 | -2.9803 |