MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems
Paper
•
2410.13716
•
Published
🏜️MIRAGE-Bench [NAACL'25]
Dataset Collection from the MIRAGE-Bench paper
-
-
nthakur/mirage-bench
Viewer • Updated • 13k • 245 • 2 -
nthakur/mirage-bench-output
Viewer • Updated • 10k • 84 • 1 -
nthakur/mirage-bench-pairwise-judgments
Viewer • Updated • 299k • 52 • 1 -
nthakur/mirage-bench-instruct
Viewer • Updated • 39.8k • 11 • 1 -
nthakur/mirage-bench-sft-teacher-gpt-4o
Viewer • Updated • 29.2k • 7 • 2 -
nthakur/mirage-bench-sft-teacher-mixtral
Viewer • Updated • 55.6k • 1 -
nthakur/mirage-bench-sft-teacher-llama-3
Viewer • Updated • 52.6k • 1 • 3
nthakur/Mistral-7B-Instruct-v0.2-mirage-bench-sft
Updated • 9Note GPT-4o knowledge distilled into Mistral-7B-Instruct-v0.2 (Best Model)
nthakur/Meta-Llama-3-8B-Instruct-mirage-bench-sft
Updated • 10Note GPT-4o knowledge distilled into Mistral-7B-Instruct-v0.2
nthakur/Mistral-7B-Instruct-v0.2-mirage-bench-sft-teacher-mixtral
Updated • 6Note Mixtral-8x22B-Instruct-v0.1 & Mistral-7B-Instruct-v0.2 knowledge distilled into Mistral-7B-Instruct-v0.2
nthakur/Meta-Llama-3-8B-Instruct-mirage-bench-sft-teacher-llama-3
Updated • 13Note Meta-Llama-3-70B-Instruct & Meta-Llama-8B-Instruct knoweldge distilled into Meta-Llama-3-8B-Instruct