Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Question Answering on NQ 1200 noisy contexts
Loading...
83.13
Unhelpful
Grft-requery
19.4404
35.9752
52.51
69.0448
Feb 19, 2025
Unhelpful
Random
Updated 4d ago
Evaluation Results
Method
Method
Links
Unhelpful
Random
Grft-requery
tuning=Gated ReFT, mec...
2025.02
83.13
82.2
Grft
tuning=Gated ReFT
2025.02
62.18
62.95
Astute-RAG
2025.02
60.39
68.74
System Prompt
2025.02
55.62
49.15
LLM
model=Llama-7B-Chat
2025.02
52.47
38.84
FT-Llama-Full
fine-tuning=Full
2025.02
42.35
47.98
COT
strategy=Chain-of-thought
2025.02
40.2
34.07
FT-Llama-Lora
fine-tuning=LoRA
2025.02
36.29
45.32
ICL
strategy=In-context le...
2025.02
21.89
11.5
Feedback
Search any
task
Search any
task