Hawk raises NPU kernel generation accuracy from 49.4% to 80% and yields up to 2.2× speedups by retrieving and distilling structured hardware-aware knowledge without any model training.
Rag-fusion: a new take on retrieval-augmented gener- ation
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
GeoRAG recasts RAG context selection as monotone submodular Information Demand Coverage Optimization solved via Sinkhorn-Wasserstein distance, delivering +6.5 to +7.5 EM gains over top-k on six QA benchmarks.
Introduces V-RAGBench benchmark and CARVE method that selects per-chunk retrieval configurations via parallel retrievers and adaptive reranking, outperforming eight VideoRAG baselines.
Presents RegOps-Bench benchmark and RefWalk framework for citation-closure retrieval and per-rule attribution in regulatory compliance QA, reporting substantial gains in recall and citation accuracy over baselines.
RECIPER improves procedure-oriented retrieval from materials papers by combining paragraph-level dense retrieval with LLM-extracted procedural summaries and lightweight reranking, yielding average gains of +3.73 Recall@1 and better downstream QA.
CRVA-TGRAG combines parent-document segmentation, ensemble retrieval, and teacher-guided fine-tuning to mitigate knowledge conflicts and improve accuracy in LLM-based CVE vulnerability analysis.
InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-Hop RAG via SLMs.
Three-aspect RAG query pipeline optimization for cancer patient QA introduces HSRDR and SEOS and reports 5.24% accuracy gain on Claude-3-haiku versus chain-of-thought on a custom dataset.
citing papers explorer
-
Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation
Hawk raises NPU kernel generation accuracy from 49.4% to 80% and yields up to 2.2× speedups by retrieving and distilling structured hardware-aware knowledge without any model training.
-
Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation
GeoRAG recasts RAG context selection as monotone submodular Information Demand Coverage Optimization solved via Sinkhorn-Wasserstein distance, delivering +6.5 to +7.5 EM gains over top-k on six QA benchmarks.
-
Rethinking RAG in Long Videos: What to Retrieve and How to Use It?
Introduces V-RAGBench benchmark and CARVE method that selects per-chunk retrieval configurations via parallel retrievers and adaptive reranking, outperforming eight VideoRAG baselines.
-
Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering
Presents RegOps-Bench benchmark and RefWalk framework for citation-closure retrieval and per-rule attribution in regulatory compliance QA, reporting substantial gains in recall and citation accuracy over baselines.
-
RECIPER: A Dual-View Retrieval Pipeline for Procedure-Oriented Materials Question Answering
RECIPER improves procedure-oriented retrieval from materials papers by combining paragraph-level dense retrieval with LLM-extracted procedural summaries and lightweight reranking, yielding average gains of +3.73 Recall@1 and better downstream QA.
-
Tug-of-War within A Decade: Conflict Resolution in Vulnerability Analysis via Teacher-Guided Retrieval-Augmented Generations
CRVA-TGRAG combines parent-document segmentation, ensemble retrieval, and teacher-guided fine-tuning to mitigate knowledge conflicts and improve accuracy in LLM-based CVE vulnerability analysis.
-
Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking
InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-Hop RAG via SLMs.
-
Query pipeline optimization for cancer patient question answering systems
Three-aspect RAG query pipeline optimization for cancer patient QA introduces HSRDR and SEOS and reports 5.24% accuracy gain on Claude-3-haiku versus chain-of-thought on a custom dataset.