LazyAttention kernelizes deferred positional encoding to enable zero-copy, position-agnostic KV cache reuse, delivering 1.37× lower TTFT and 1.40× higher throughput than Block-Attention under skewed document distributions while preserving output quality.
Retrieval-based language models and applications
5 Pith papers cite this work, alongside 74 external citations. Polarity classification is still indexing.
5
Pith papers citing it
74
external citations · OpenAlex
representative citing papers
Continued pretraining of Code Llama on Proof-Pile-2 yields Llemma, an open math-specialized LLM that beats known open base models on MATH and supports tool use plus formal proving out of the box.
Multilingual RAG rerankers exhibit language bias that limits cross-lingual evidence use, and the proposed LAURA method aligns ranking with downstream generation utility to reduce the bias and improve performance.
Adding handwritten Cypher graph tools to an agentic RAG system roughly doubled factual-correctness precision and recall on MoNaCo complex questions and improved fine-grained truthfulness compared with vector-only RAG.
Cluster-based semantic chunking does not outperform fixed-size or recursive chunking for RAG on academic theses, and RAGAs faithfulness shows limited reliability in this setup.
citing papers explorer
-
LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding
LazyAttention kernelizes deferred positional encoding to enable zero-copy, position-agnostic KV cache reuse, delivering 1.37× lower TTFT and 1.40× higher throughput than Block-Attention under skewed document distributions while preserving output quality.
-
Llemma: An Open Language Model For Mathematics
Continued pretraining of Code Llama on Proof-Pile-2 yields Llemma, an open math-specialized LLM that beats known open base models on MATH and supports tool use plus formal proving out of the box.
-
All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
Multilingual RAG rerankers exhibit language bias that limits cross-lingual evidence use, and the proposed LAURA method aligns ranking with downstream generation utility to reduce the bias and improve performance.
-
Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)
Adding handwritten Cypher graph tools to an agentic RAG system roughly doubled factual-correctness precision and recall on MoNaCo complex questions and improved fine-grained truthfulness compared with vector-only RAG.
-
Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts
Cluster-based semantic chunking does not outperform fixed-size or recursive chunking for RAG on academic theses, and RAGAs faithfulness shows limited reliability in this setup.