~ similar to 2610.32933· 20 results
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 MIMO, a two-stage framework that improves Multilingual Information Retrieval (MLIR) by stabilizing cross-lingual alignment and enhancing retrieval discrimination using a combination…
Yunfei Zhong, Jun Yang, Wei Huang, Yinqiong Cai +6 more
The authors present Querit-Reranker, a family of multilingual cross-encoder rerankers that can adapt to new target distributions with minimal task-specific relevance annotations.
The authors adapt NVIDIA's Nemotron retrieval stack for Modern Greek, improving retrieval performance and introducing a new benchmark called HERA.
This paper proposes a neural architecture for Quranic Passage Retrieval using hybrid candidate retrieval, semantic reranking, confidence gating, and multi-verse aggregation.
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.
This paper introduces robustness indicators to systematically analyze how multilingual text embedding model rankings change based on dataset composition and aggregation methods, revealing that only a…
Xuan Lu, Haohang Huang, Yingqi Fan, Junlong Tong +4 more
This paper proposes CompRank, a token-efficient reranking framework for large language models that reduces redundant computation and achieves strong reranking performance.
This paper proposes a multi-turn retrieval-augmented generation pipeline for conversational systems across four domains.
Zhe Xu, Prachi Agrawal, Kavosh Asadi, Tianyi Chen +16 more
This paper adapts Large Language Models as semantic representation backbones in a two-tower retrieval architecture for high-throughput, large-scale recommendation systems.
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.
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.
This paper introduces ScoreGate, a method for controlling retrieval cardinality at inference time using existing scores, reducing over-retrieval and under-retrieval.
This paper introduces RAGAL, a retrieval-augmented assistant for technical support teams, built under three constraints: zero data egress, read-only, and limited resources. The highest-leverage invest…
The paper presents an open-source recipe for training retrieval models using English data and studies its transferability to multilingual retrieval through translate-train.
The paper proposes DART, a test-time adaptation method that enhances zero-resource dense retrieval reranking by adaptively tuning a bilinear scoring matrix using pseudo-positive and pseudo-negative ex…