GQR is a test-time optimization technique that refines primary retriever query embeddings using complementary retriever scores to achieve high performance with smaller representations in multimodal visual document retrieval.
Rocketqa: An optimized training approach to dense passage retrieval for open-domain question answering.arXiv preprint arXiv:2010.08191
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual, and long-document retrieval benchmarks.
C-Pack releases a new Chinese embedding benchmark, large training dataset, and optimized models that outperform priors by up to 10% on C-MTEB while also delivering English SOTA results.
Larger 100K vocabularies in SPLADE models, especially those initialized with ESPLADE pretraining, improve retrieval effectiveness after pruning compared to 32K baselines while keeping similar efficiency.
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
citing papers explorer
-
Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization
GQR is a test-time optimization technique that refines primary retriever query embeddings using complementary retriever scores to achieve high performance with smaller representations in multimodal visual document retrieval.
-
M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual, and long-document retrieval benchmarks.
-
C-Pack: Packed Resources For General Chinese Embeddings
C-Pack releases a new Chinese embedding benchmark, large training dataset, and optimized models that outperform priors by up to 10% on C-MTEB while also delivering English SOTA results.
-
The Role of Vocabularies in Learning Sparse Representations for Ranking
Larger 100K vocabularies in SPLADE models, especially those initialized with ESPLADE pretraining, improve retrieval effectiveness after pruning compared to 32K baselines while keeping similar efficiency.
-
A Survey of Scaling in Large Language Model Reasoning
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.