Factual Correction on CONFLICTS
97ROUGEFACTCORRECTOR
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| FACTCORRECTORBase LLM=granite-4.0-h-tiny2026.01 | 97 | 95 | 0.86 | 0.97 | |
| FACTCORRECTORBase LLM=mixtral-8x22b-instruct2026.01 | 89 | 87 | 0.73 | 0.87 | |
| RACBase LLM=llama-3.3-70b-instruct2026.01 | 87 | 77 | 0.65 | 0.77 | |
| RACBase LLM=gpt-oss-120b2026.01 | 85 | 60 | 0.74 | 0.89 | |
| FACTCORRECTORBase LLM=granite-4.0-h-small2026.01 | 83 | 76 | 0.58 | 0.78 | |
| RACBase LLM=granite-4.0-h-tiny2026.01 | 83 | 59 | 0.67 | 0.84 | |
| RACBase LLM=granite-4.0-h-small2026.01 | 74 | 48 | 0.49 | 0.73 | |
| FACTCORRECTORBase LLM=llama-3.3-70b-instruct2026.01 | 73 | 62 | 0.46 | 0.6 | |
| FACTCORRECTORBase LLM=gpt-oss-120b2026.01 | 72 | 66 | 0.44 | 0.66 | |
| CRITICBase LLM=granite-4.0-h-tiny2026.01 | 55 | 49 | 0.08 | 0.77 | |
| RACBase LLM=mixtral-8x22b-instruct2026.01 | 54 | 23 | 0.29 | 0.87 | |
| LLM2Base LLM=granite-4.0-h-small2026.01 | 42 | 15 | -0.1 | 0.13 | |
| LLM2Base LLM=granite-4.0-h-tiny2026.01 | 38 | 15 | -0.23 | 0.29 | |
| CRITICBase LLM=llama-3.3-70b-instruct2026.01 | 32 | 15 | -0.36 | 0.31 | |
| LLM1Base LLM=granite-4.0-h-tiny2026.01 | 22 | 8 | -0.44 | 0.4 | |
| LLM2Base LLM=llama-3.3-70b-instruct2026.01 | 21 | 4 | -0.46 | 0.06 | |
| LLM2Base LLM=mixtral-8x22b-instruct2026.01 | 20 | 5 | -0.48 | 0.1 | |
| LLM1Base LLM=llama-3.3-70b-instruct2026.01 | 19 | 3 | -0.62 | 0.17 | |
| LLM2Base LLM=gpt-oss-120b2026.01 | 16 | 2 | -0.54 | 0.19 | |
| LLM1Base LLM=mixtral-8x22b-instruct2026.01 | 15 | 2 | -0.63 | 0.3 | |
| CRITICBase LLM=granite-4.0-h-small2026.01 | 15 | 3 | -0.69 | 0.2 | |
| LLM1Base LLM=granite-4.0-h-small2026.01 | 15 | 2 | -0.68 | 0.17 | |
| CRITICBase LLM=mixtral-8x22b-instruct2026.01 | 14 | 2 | -0.69 | 0.41 | |
| CRITICBase LLM=gpt-oss-120b2026.01 | 12 | 1 | -0.89 | 0.09 | |
| LLM1Base LLM=gpt-oss-120b2026.01 | 8 | 0 | -0.83 | 0.37 |