Back to Arena

REALM

by Google Research (Guu et al.)

System Card

OrganizationGoogle Research (Guu et al.)
Released2020-02
Architecturevector-rag / Latent retriever pretrained with MLM backprop
DetailsAugments LM pretraining with a latent knowledge retriever that attends over millions of documents. Retriever is trained unsupervised by masked-LM loss backpropagating through the retrieval step.
Parameters—
Domainrag-retrievalknowledge-graph
Open SourceYes
PaperView Paper
CodeRepository
icml-2020pretraininglatent-retrieverwikipedia

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
68.625p
NIAH
no data
LooGLE
no data
LongBench
603p
∞Bench
no data
Multi-Turn Recall
0/2
LoCoMo
no data
MemoryBank
no data
Cross-Session Memory
1/1
LongMemEval
59.19p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
65.627p
HotpotQA
64.328p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
63.10p
Sources:REALM paper (arXiv:2002.08909); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)REALM paper (arXiv:2002.08909); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)REALM paper (arXiv:2002.08909); evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)REALM paper (arXiv:2002.08909); evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)REALM paper (arXiv:2002.08909); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)REALM paper (arXiv:2002.08909); evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)