Prism-Reranker models output relevance, contribution statements, and evidence passages to support agentic retrieval beyond scalar scoring.
Improving efficient neural ranking models with cross-architecture knowledge distil- lation.arXiv preprint arXiv:2010.02666
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
representative citing papers
A single model unifies retrieval and context compression for on-device RAG via shared representations, matching traditional RAG performance at 1/10 context size with no extra storage.
SPLADE models produce wacky expansion terms whose prevalence rises with larger vocabularies and falls with stricter sparsity; these terms primarily aid in-domain retrieval rather than out-of-domain generalization.
LEAF distills teacher-aligned student embedding models that achieve new SOTA results on BEIR and MTEB for their size class while requiring only modest data and compute.
Fine-tuning a Spanish biomedical encoder on Gemini-generated synthetic data for multiple languages yields a bi-encoder that matches or exceeds BioBERT-ST on clinical code retrieval metrics, with further gains from cross-encoder reranking on most languages.
Stratified sampling preserving teacher score distribution outperforms hard-negative mining as a robust baseline for knowledge distillation in dense retrieval.
A distillation-plus-task-contrastive training regimen yields compact embedding models that match or exceed state-of-the-art performance for their size while supporting 32k-token contexts and quantization.
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.
CoveR improves nugget coverage by 10% over dense baselines in long-form RAG via coverage-aware contrastive training on LLM-generated sub-question signals without losing relevance performance.
A hybrid supervision method for bi-encoder retrievers combines graded relevance from teacher models, production retrieval priors, and selective engagement to improve relevance and NDCG over Walmart's current sponsored search system.
citing papers explorer
-
Understanding Wacky Weights: A Dissection of SPLADE's Learned Term Importance
SPLADE models produce wacky expansion terms whose prevalence rises with larger vocabularies and falls with stricter sparsity; these terms primarily aid in-domain retrieval rather than out-of-domain generalization.
-
LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations
LEAF distills teacher-aligned student embedding models that achieve new SOTA results on BEIR and MTEB for their size class while requiring only modest data and compute.