Claim Correction on SciFact Retrieved evidence
41.7093SARI ScoreM2C
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| M2CLLM=Qwen-2.5 (32B), Ranker=MonoT5, Masking=Diversity-aware (DM)2026.04 | 41.7093 | -2.845 | |
| M2Cw/VerLLM=Qwen-2.5 (32B), Ranker=MonoT52026.04 | 40.938 | -2.7091 | |
| M2CLLM=Llama-2.0 (70B), Ranker=MonoT5, Masking=Diversity-aware (DM)2026.04 | 39.694 | -2.9304 | |
| M2CLLM=Qwen-2.5 (32B), Ranker=RM3, Masking=Diversity-aware (DM)2026.04 | 39.1719 | -2.9198 | |
| M2C+LLM=Qwen-2.5 (32B), Ranker=n/a, Masking=Diversity-aware (DM)2026.04 | 38.4647 | -2.8636 | |
| M2CLLM=Qwen-2.5 (32B), Ranker=ColBERT, Masking=Diversity-aware (DM)2026.04 | 37.749 | -2.9198 | |
| M2C+LLM=Llama-2.0 (70B), Ranker=n/a, Masking=Diversity-aware (DM)2026.04 | 37.582 | -2.9302 | |
| M2CLLM=Qwen-2.5 (32B), Ranker=Contriever, Masking=Diversity-aware (DM)2026.04 | 37.1282 | -2.9282 | |
| M2CLLM=Llama-2.0 (70B), Ranker=Contriever, Masking=Diversity-aware (DM)2026.04 | 37.1026 | -2.9409 | |
| M2CLLM=Llama-2.0 (70B), Ranker=RM3, Masking=Diversity-aware (DM)2026.04 | 36.8477 | -2.9852 | |
| M2CLLM=Llama-2.0 (70B), Ranker=ColBERT, Masking=Diversity-aware (DM)2026.04 | 36.4724 | -2.9212 | |
| RAGLLM=Qwen-2.5 (32B), Ranker=MonoT52026.04 | 36.3252 | -2.4655 | |
| 0-shotLLM=Qwen-2.5 (32B), Ranker=n/a2026.04 | 35.7045 | -3.0843 | |
| M2CLLM=Qwen-2.5 (32B), Ranker=BM25, Masking=Diversity-aware (DM)2026.04 | 35.6633 | -2.8656 | |
| 0-shotLLM=Llama-2.0 (70B), Ranker=n/a2026.04 | 35.0145 | -2.999 | |
| M2CLLM=Llama-2.0 (70B), Ranker=BM25, Masking=Diversity-aware (DM)2026.04 | 34.8178 | -2.9862 | |
| RAGLLM=Llama-2.0 (70B), Ranker=MonoT52026.04 | 34.3641 | -2.6404 | |
| M2Cw/VerLLM=Llama-2.0 (70B), Ranker=MonoT52026.04 | 34.2985 | -2.9546 | |
| ZeroFeC-DALLM=n/a, Predictor=ZeroFeC-DA, Ranker=MonoT52026.04 | 32.1194 | -3.1905 | |
| COMPEDITLLM=n/a, Predictor=COMPEDIT, Ranker=MonoT52026.04 | 30.4219 | -3.1699 | |
| T5-DistantLLM=n/a, Predictor=T5-Distant, Ranker=GENRE2026.04 | 23.364 | -3.0965 |