Granite Embedding R2 Models
read the original abstract
We introduce the Granite Embedding R2 models, a comprehensive family of high-performance English encoder-based embedding models engineered for enterprise-scale dense retrieval applications. Building upon our first-generation release, these models deliver substantial improvements, including 16x expanded context length (8,192 tokens), state-of-the-art performance across diverse retrieval domains - text, code, long-document search, multi-turn conversational, and tabular data - and measurable speed advantages of 19-44\% over leading competitors while maintaining superior accuracy. Our release encompasses both bi-encoder and cross-encoder architectures, featuring a highly effective 22-layer retriever model and its efficient 12-layer counterpart, alongside a high-quality reranker model, all trained exclusively on enterprise-appropriate data with comprehensive governance oversight. The models demonstrate exceptional versatility across standard benchmarks, IBM-developed evaluation suites, and real-world enterprise use cases, establishing new performance standards for open-source embedding models. In an era where retrieval speed and accuracy are paramount for competitive advantage, the Granite R2 models deliver a compelling combination of cutting-edge performance, enterprise-ready licensing, and transparent data provenance that organizations require for mission-critical deployments. All models are publicly available under the Apache 2.0 license at https://huggingface.co/collections/ibm-granite, enabling unrestricted research and commercial use.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
DRBENCHER: Can Your Agent Identify the Entity, Retrieve Its Properties and Do the Math?
DRBENCHER generates multi-hop questions across biochemistry, finance, geophysics, security, and history that test interleaved browsing and computation, where the strongest models reach only 20% accuracy and human vali...
-
Rescaling MLM-Head for Neural Sparse Retrieval
Rescaling the MLM-head projection by a constant factor at initialization resolves scale mismatch in learned sparse retrieval and enables stable use of large-norm backbones such as ModernBERT.
-
Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks
TEmBed benchmark shows that the best tabular embedding model depends on the specific task and the representation level (cell, row, column, or table).
-
A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents
DoRA is a new synthetic benchmark for RAG-based QA on defense documents where fine-tuning Llama3.1-8B-Instruct on it improves task success by up to 26% and cuts hallucination rates by 47%.
-
A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents
DoRA generates synthetic RAG training and evaluation data from 40 defense documents, halving hallucination rates in a LoRA-adapted Llama3.1-8B compared to 8 baselines.
-
Caraman at SemEval-2026 Task 8: Three-Stage Multi-Turn Retrieval with Query Rewriting, Hybrid Search, and Cross-Encoder Reranking
A pipeline with LoRA-fine-tuned query rewriting, BM25+dense hybrid retrieval via RRF, and cross-encoder reranking reaches nDCG@5 of 0.531 on multi-turn retrieval across four domains.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.