NeocorRAG uses Evidence Chains to achieve SOTA retrieval quality in RAG on HotpotQA, 2WikiMultiHopQA, MuSiQue, and NQ for 3B and 70B models while using under 20% of the tokens of comparable methods.
Zhao, Yi Luan, Keith B
7 Pith papers cite this work, alongside 91 external citations. Polarity classification is still indexing.
7
Pith papers citing it
91
external citations · Crossref
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.
REZE controls representation shifts in contrastive pre-finetuning of text embeddings via eigenspace decomposition of anchor-positive pairs and adaptive soft-shrinkage on task-variant directions.
Search-R3 trains LLMs to output search embeddings as a direct product of step-by-step reasoning via supervised pre-training and a specialized RL environment that avoids full corpus re-encoding.
Data-CUBE applies a two-level curriculum (TSP-based task ordering via simulated annealing plus difficulty-sorted mini-batches) to multi-task instruction tuning and reports gains on MTEB sentence representation tasks.