Formalizes continual model routing (CMR), releases CMRBench with over 2000 models, and presents CARvE which outperforms retrieval, fine-tuning and adapter-merging baselines on model/family/domain accuracy.
SPLADE : Sparse Lexical and Expansion Model for First Stage Ranking
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
LLM-based dense retrievers generalize better when instruction-tuned but pay a specialization tax when optimized for reasoning; they resist typos and corpus poisoning better than encoder-only baselines yet remain vulnerable to semantic perturbations, with larger models and certain embedding geometry,
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.
Agentic program search over a frozen encoder API yields retrieval programs that improve nDCG@10 on held-out tasks and unseen encoder families with no per-domain training.
KAHM yields a compute-efficient query encoder that outperforms matched learned adapters in reconstructing a frozen Mixedbread embedding space on an Austrian-law retrieval task while delivering an 8.53x CPU speedup.
Introduces a parameter-driven framework for data attribution in LLMs that enables negotiation among creators, users, and intermediaries to meet stakeholder goals within the data economy.
Combining contrastive loss with KLD distillation and adding sparsity regularization improves effectiveness and reduces FLOPS by 2x in conversational search with minimal recall loss.
Introduces FARO, a scalable quadratic optimization approach for fairness-aware top-k retrieval in RAG that mitigates generation bias via controlled reranking and position-aware propagation modeling.
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
-
Continual Model Routing in Evolving Model Hubs
Formalizes continual model routing (CMR), releases CMRBench with over 2000 models, and presents CARvE which outperforms retrieval, fine-tuning and adapter-merging baselines on model/family/domain accuracy.
-
On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability
LLM-based dense retrievers generalize better when instruction-tuned but pay a specialization tax when optimized for reasoning; they resist typos and corpus poisoning better than encoder-only baselines yet remain vulnerable to semantic perturbations, with larger models and certain embedding geometry,
-
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.
-
Test-Time Compute for Frozen Embedding Models through Agentic Program Search
Agentic program search over a frozen encoder API yields retrieval programs that improve nDCG@10 on held-out tasks and unseen encoder families with no per-domain training.
-
Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces
KAHM yields a compute-efficient query encoder that outperforms matched learned adapters in reconstructing a frozen Mixedbread embedding space on an Austrian-law retrieval task while delivering an 8.53x CPU speedup.
-
A Human-Centric Framework for Data Attribution in Large Language Models
Introduces a parameter-driven framework for data attribution in LLMs that enables negotiation among creators, users, and intermediaries to meet stakeholder goals within the data economy.
-
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.
-
Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation
Introduces FARO, a scalable quadratic optimization approach for fairness-aware top-k retrieval in RAG that mitigates generation bias via controlled reranking and position-aware propagation modeling.
-
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.
- From Tokens to Concepts: Leveraging SAE for SPLADE