MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems
Paper
•
2410.13716
•
Published
BEIR
university
AI & ML interests
BEIR (Benchmarking IR) consists of a homogenous benchmark for diverse sentence or passage level IR tasks. It provides a common and easy framework for the cross-domain evaluation of your retrieval models.
Recent Activity
View all activity
BeIR's activity
nthakur
authored
a
paper
about 2 months ago
nthakur
authored
a
paper
4 months ago
Post
3300
🦢 The SWIM-IR dataset contains 29 million text-retrieval training pairs across 27 diverse languages. It is one of the largest synthetic multilingual datasets generated using PaLM 2 on Wikipedia! 🔥🔥
SWIM-IR dataset contains three subsets :
- Cross-lingual:
- Monolingual:
- Indic Cross-lingual:
Check it out:
https://huggingface.co/collections/nthakur/swim-ir-dataset-662ddaecfc20896bf14dd9b7
SWIM-IR dataset contains three subsets :
- Cross-lingual:
nthakur/swim-ir-cross-lingual- Monolingual:
nthakur/swim-ir-monolingual- Indic Cross-lingual:
nthakur/indic-swim-ir-cross-lingualCheck it out:
https://huggingface.co/collections/nthakur/swim-ir-dataset-662ddaecfc20896bf14dd9b7
nthakur
authored
9
papers
12 months ago
Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard
Paper
•
2306.07471
•
Published
NoMIRACL: Knowing When You Don't Know for Robust Multilingual Retrieval-Augmented Generation
Paper
•
2312.11361
•
Published
•
1
HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution
Paper
•
2307.16883
•
Published
Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks
Paper
•
2010.08240
•
Published
Evaluating Embedding APIs for Information Retrieval
Paper
•
2305.06300
•
Published
•
1
GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval
Paper
•
2112.07577
•
Published
Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages
Paper
•
2210.09984
•
Published
•
2
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
Paper
•
2104.08663
•
Published
•
3
Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval
Paper
•
2311.05800
•
Published
•
3
nreimers
authored
a
paper
almost 2 years ago
nreimers
updated
a
model
over 3 years ago