~ similar to 2606.23642· 20 results
Lixuan Guo, Yifei Wang, Tiansheng Wen, Aosong Feng +2 more
The paper introduces Single-stage Sparse Retrieval (SSR), a method that replaces computationally expensive vector clustering with sparse autoencoding to achieve highly efficient multi-vector retrieval…
Tingyu Song, Mingxin Li, Yanzhao Zhang, Dingkun Long +4 more
The paper introduces UEmbed, a decoder-only multimodal embedding model that produces both sparse lexical and dense representations in one forward pass.
The paper proposes SCAR, an adaptive retrieval policy that improves recall in Retrieval-Augmented Generation by selectively expanding neighboring chunks.
Kehang Jia, Teng Liu, Juntao Li, Hua Chen +3 more
The paper proposes AntEmbed, a dual-mode multimodal embedding model for efficient retrieval and reasoning-enhanced fine-grained matching.
LongAttnComp introduces a novel, two-stage fine-tuning framework for context compression that significantly improves long-context reasoning performance, matching or exceeding full-context accuracy on…
Yuxiang Guo, Zhonghao Hu, Yuren Mao, Yuhang Liu +4 more
This paper presents Stellar, a scalable multimodal document retrieval framework that reduces memory overhead and query latency without compromising retrieval effectiveness.
The paper proposes lightweight fine-tuning as an alternative to pooling-aware training for reducing vector count in late interaction models, achieving broad gains and high compression rates.
The paper introduces Self-Conditioned Positional HNSW (SCP-HNSW), a method that modifies chunk embeddings and retrieval process to mitigate redundant evidence retrieval from overlapping document chunk…
This paper proves that single-vector embeddings require a larger representation size than multi-vector embeddings to approximate certain similarities.
This paper proposes a unified multi-task framework for handling six different entity pair relationship types in e-commerce with a shared relevance model.
This paper introduces PLAID-PRF, a method for performing Pseudo-Relevance Feedback (PRF) over PLAID, a centroid-based dense retrieval model, to improve retrieval effectiveness.
This paper proposes a new paradigm for information retrieval using dense embeddings, called Non-Negative elastic Net (NNN) decoding, which selects documents jointly with the context of the entire corp…
The paper proposes InSemRAG, an enhanced RAG framework that improves retrieval accuracy and knowledge integrity by incorporating intent-aware retrieval and semantics-preserving chunking, achieving sta…
This paper compares three methods for answering questions over legal documents: full-corpus injection, embedding retrieval, and LLM navigation over a compact structured index. The results show that th…
This study systematically evaluates a wide range of chunking methods for Retrieval-Augmented Generation (RAG) to assess their effectiveness and highlight the overlooked challenges associated with chun…
This paper introduces SVD-RAG, a cost-efficient and content-adaptive summarization method for hierarchical Retrieval-Augmented Generation systems using Singular Value Decomposition on dense sentence e…