Question Answering on MuSiQue entity-level knowledge conflict (test)
7.7Mean RankFaithfulRAG
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FaithfulRAGBackbone LLM=mistral-7b-instruct, Category=Context-faithful Decoding2025.06 | 7.7 | 78.5 | |
| COIECDBackbone LLM=llama3.1-8b-instruct, Category=Context-faithful Decoding2025.06 | 9.2 | 70.5 | |
| COIECDBackbone LLM=qwen2.5-7b-instruct, Category=Context-faithful Decoding2025.06 | 9.8 | 69.7 | |
| COIECDBackbone LLM=mistral-7b-instruct, Category=Context-faithful Decoding2025.06 | 10.3 | 66.8 | |
| Opin(Instr)Backbone LLM=llama3.1-8b-instruct, Category=Context-faithful Prompting2025.06 | 11.3 | 70.3 | |
| CADBackbone LLM=mistral-7b-instruct, Category=Context-faithful Decoding2025.06 | 11.8 | 63.6 | |
| FaithfulRAGBackbone LLM=llama3.1-8b-instruct, Category=Context-faithful Decoding2025.06 | 11.8 | 79.9 | |
| CADBackbone LLM=qwen2.5-7b-instruct, Category=Context-faithful Decoding2025.06 | 12.4 | 78.6 | |
| ATTRBackbone LLM=mistral-7b-instruct, Category=Context-faithful Prompting2025.06 | 12.7 | 66.1 | |
| CADBackbone LLM=llama3.1-8b-instruct, Category=Context-faithful Decoding2025.06 | 12.8 | 72.6 | |
| Opin(Instr)Backbone LLM=mistral-7b-instruct, Category=Context-faithful Prompting2025.06 | 13.1 | 68.1 | |
| FaithfulRAGBackbone LLM=qwen2.5-7b-instruct, Category=Context-faithful Decoding2025.06 | 13.8 | 78 | |
| ATTRBackbone LLM=qwen2.5-7b-instruct, Category=Context-faithful Prompting2025.06 | 14 | 78.7 | |
| KREBackbone LLM=llama3.1-8b-instruct, Category=Context-faithful Decoding2025.06 | 14 | 35.9 | |
| ATTRBackbone LLM=llama3.1-8b-instruct, Category=Context-faithful Prompting2025.06 | 14.7 | 62.8 | |
| Opin(Instr)Backbone LLM=qwen2.5-7b-instruct, Category=Context-faithful Prompting2025.06 | 15.3 | 76.9 | |
| ChatQA-2.0Backbone LLM=Llama3.1-8B, Category=Specific RAG Models2025.06 | 15.5 | 77.2 | |
| OriginBackbone LLM=mistral-7b-instruct, Category=With Full Context2025.06 | 15.9 | 67.6 | |
| KREBackbone LLM=mistral-7b-instruct, Category=Context-faithful Decoding2025.06 | 16.3 | 50.6 | |
| OriginBackbone LLM=qwen2.5-7b-instruct, Category=With Full Context2025.06 | 17.3 | 75.2 | |
| OriginBackbone LLM=llama3.1-8b-instruct, Category=With Full Context2025.06 | 17.6 | 67.8 | |
| ChatQA-1.5Backbone LLM=Llama3.1-8B, Category=Specific RAG Models2025.06 | 17.7 | 75 | |
| KREBackbone LLM=qwen2.5-7b-instruct, Category=Context-faithful Decoding2025.06 | 18.6 | 70.7 | |
| Self-RAGBackbone LLM=Llama2-7B, Category=Specific RAG Models2025.06 | 18.8 | 54.1 |