Conversational Question Answering on Abg-CoQA Ambiguous
72.9Overlap F1IntentRL
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| IntentRLModel=4B Instruct, Output Format=Interpretation-Answer Pairs2025.11 | 72.9 | 78.1 | 53.5 | 61 | |
| IntentPromptModel=235B MoE Instruct, Output Format=Interpretation-Answer Pairs2025.11 | 55.2 | 63.1 | 47 | 45.5 | |
| IntentPromptModel=4B Instruct, Output Format=Answer-only2025.11 | 48.5 | 58.5 | 42.6 | 35.8 | |
| IntentPromptModel=235B MoE Instruct, Output Format=Answer-only2025.11 | 47.8 | 62.7 | 52.2 | 39.8 | |
| IntentPromptModel=235B MoE Thinking, Output Format=Interpretation-Answer Pairs2025.11 | 47.8 | 66.2 | 49.7 | 50.4 | |
| IntentPromptModel=235B MoE Thinking, Output Format=Answer-only2025.11 | 44.6 | 70.4 | 51.9 | 55.3 | |
| IntentPromptModel=4B Instruct, Output Format=Interpretation-Answer Pairs2025.11 | 44.4 | 62.3 | 42.7 | 45.5 | |
| SFTModel=4B Instruct, Output Format=Answer-only2025.11 | 40.1 | 48.1 | 70.3 | 20.3 | |
| IntentPromptModel=4B Thinking, Output Format=Answer-only2025.11 | 31.3 | 60.4 | 52.6 | 37.4 | |
| IntentPromptModel=4B Thinking, Output Format=Interpretation-Answer Pairs2025.11 | 18.2 | 46.2 | 45.3 | 31.7 |