MaxSim similarity can exactly replicate inner products of non-negative sparse vectors of arbitrary dimension, and a proposed Signed MaxSim extension enables exact replication for arbitrary real-valued vectors.
ISBN 9781450360142
4 Pith papers cite this work, alongside 179 external citations. Polarity classification is still indexing.
4
Pith papers citing it
179
external citations · external index
years
2026 4representative citing papers
Combining contrastive loss with KLD distillation and adding sparsity regularization improves effectiveness and reduces FLOPS by 2x in conversational search with minimal recall loss.
Granite Embedding Multilingual R2 releases 311M and 97M parameter bi-encoder models that achieve state-of-the-art retrieval performance on multilingual text, code, long-document, and reasoning datasets.
A multi-turn RAG system combines learned sparse retrieval with LLM-conditioned rewriting, listwise reranking, and generation to handle conversational QA and unanswerable queries across four domains.
citing papers explorer
-
Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models
MaxSim similarity can exactly replicate inner products of non-negative sparse vectors of arbitrary dimension, and a proposed Signed MaxSim extension enables exact replication for arbitrary real-valued vectors.
-
Improving the Efficiency and Effectiveness of LLM Knowledge Distillation for Conversational Search
Combining contrastive loss with KLD distillation and adding sparsity regularization improves effectiveness and reduces FLOPS by 2x in conversational search with minimal recall loss.
-
Granite Embedding Multilingual R2 Models
Granite Embedding Multilingual R2 releases 311M and 97M parameter bi-encoder models that achieve state-of-the-art retrieval performance on multilingual text, code, long-document, and reasoning datasets.
-
uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking
A multi-turn RAG system combines learned sparse retrieval with LLM-conditioned rewriting, listwise reranking, and generation to handle conversational QA and unanswerable queries across four domains.