Question Answering on FaithEval
81.7AccuracyFaithfulRAG
Evaluation Results
| Method | Links | |
|---|---|---|
| FaithfulRAGBackbone LLM=mistral-7b-instruct2025.06 | 81.7 | |
| FaithfulRAGBackbone LLM=llama3.1-8b-instruct2025.06 | 79.8 | |
| KREBackbone LLM=mistral-7b-instruct2025.06 | 73.2 | |
| FaithfulRAGBackbone LLM=qwen2.5-7b-instruct2025.06 | 71.8 | |
| Opin(Instr)Backbone LLM=llama3.1-8b-instruct2025.06 | 68.1 | |
| COIECDBackbone LLM=llama3.1-8b-instruct2025.06 | 67.7 | |
| CADBackbone LLM=llama3.1-8b-instruct2025.06 | 66.2 | |
| ChatQA-2.0Backbone LLM=Llama3.1-8B2025.06 | 65.2 | |
| ATTRBackbone LLM=llama3.1-8b-instruct2025.06 | 63.8 | |
| ATTRBackbone LLM=mistral-7b-instruct2025.06 | 63.6 | |
| Origin model with full contextBackbone LLM=llama3.1-8b-instruct2025.06 | 63.3 | |
| COIECDBackbone LLM=mistral-7b-instruct2025.06 | 62.8 | |
| Opin(Instr)Backbone LLM=mistral-7b-instruct2025.06 | 62.5 | |
| COIECDBackbone LLM=qwen2.5-7b-instruct2025.06 | 62.3 | |
| Origin model with full contextBackbone LLM=mistral-7b-instruct2025.06 | 61.9 | |
| CADBackbone LLM=qwen2.5-7b-instruct2025.06 | 60.5 | |
| CADBackbone LLM=mistral-7b-instruct2025.06 | 60.2 | |
| KREBackbone LLM=qwen2.5-7b-instruct2025.06 | 59.6 | |
| ATTRBackbone LLM=qwen2.5-7b-instruct2025.06 | 58.1 | |
| Opin(Instr)Backbone LLM=qwen2.5-7b-instruct2025.06 | 56.7 | |
| ChatQA-1.5Backbone LLM=Llama3.1-8B2025.06 | 56.2 | |
| Origin model with full contextBackbone LLM=qwen2.5-7b-instruct2025.06 | 53.1 | |
| KREBackbone LLM=llama3.1-8b-instruct2025.06 | 51.6 | |
| Self-RAGBackbone LLM=Llama2-7B2025.06 | 37.4 | |
| Origin model without contextBackbone LLM=llama3.1-8b-instruct2025.06 | 7.6 | |
| Origin model without contextBackbone LLM=mistral-7b-instruct2025.06 | 6.3 | |
| Origin model without contextBackbone LLM=qwen2.5-7b-instruct2025.06 | 4.2 |