RST Discourse Parsing on Instr-DT (test)
79.1Span F1Llama 2 (70B)
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Llama 2 (70B)Parsing Strategy=Bottom-up, Backbone=Llama 2, Parameters=70B, Quantization=QLoRA 4-bit2024.03 | 79.1 | 60.4 | 55.1 | 47.3 | |
| Kobayashi et al.Parsing Strategy=Bottom-up, Backbone=DeBERTa-base, Parameters=140M2024.03 | 77.8 | 60 | 51.4 | 44.4 | |
| Llama 2 (13B)Parsing Strategy=Bottom-up, Backbone=Llama 2, Parameters=13B, Quantization=QLoRA 4-bit2024.03 | 77.4 | 60.4 | 52.1 | 46.1 | |
| Kobayashi et al.Parsing Strategy=Top-down, Backbone=DeBERTa-base, Parameters=140M2024.03 | 77.3 | 57.9 | 50 | 43.4 | |
| Llama 2 (7B)Parsing Strategy=Bottom-up, Backbone=Llama 2, Parameters=7B, Quantization=QLoRA 4-bit2024.03 | 76.7 | 58.2 | 48.5 | 43.5 | |
| Llama 2 (70B)Parsing Strategy=Top-down, Backbone=Llama 2, Parameters=70B, Quantization=QLoRA 4-bit2024.03 | 76.2 | 57.1 | 53.1 | 45.2 | |
| Llama 2 (7B)Parsing Strategy=Top-down, Backbone=Llama 2, Parameters=7B, Quantization=QLoRA 4-bit2024.03 | 75.7 | 56.2 | 49.8 | 43.6 | |
| Llama 2 (13B)Parsing Strategy=Top-down, Backbone=Llama 2, Parameters=13B, Quantization=QLoRA 4-bit2024.03 | 75.7 | 57.3 | 50.2 | 43.6 |