Context-aware Instruction Following on Avocado Emails (test)
8.31Overlap (with context)GPT-4-turbo
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4-turboMode=zero-shot LLM with context (upper bound)2024.03 | 8.31 | 7.71 | 8.05 | |
| Qwen-Chat(v1.5) + Qwen-Chat(v1.5) (Logit-based CoGenesis)Mode=mixed-scale collaboration, Params=mixed2024.03 | 6.66 | 5.7 | 7.12 |