The paper introduces DEPT, a method that trains a single decoder-only large language model to both expand queries and encode documents for retrieval. By preserving document embeddings close to their initial cached values while allowing gradients to flow through the generator, DEPT stabilizes retrieval targets and enables efficient index reuse and online hard‑negative mining. Experiments on the BEIR benchmark with Qwen3‑4B‑Instruct‑2507 and LLaMA‑3.2‑3B‑Instruct show that DEPT outperforms training‑free, independently trained, and staged unified baselines, with ablations confirming the benefits of preservation, whitening, end‑to‑end expansion training, and online negatives.
By Jingyuan Wang, Richong Zhang, Zhijie Nie, Mingxin Li, Yanzhao Zhang
arXiv:2605. 11374v5 Announce Type: replace Abstract: Test-time compute is widely believed to benefit only large reasoning models, leaving small models with nothing to gain.
By Han Xiao
arXiv:2606. 29706v1 Announce Type: cross Abstract: Telecom question answering (QA) is a challenging setting for retrieval-augmented generation (RAG): evidence is fragmented across standards, papers, encyclopedic resources, and web documents, and answers often hinge on technical tables, equations, and specialized protocol language.
By Heshan Fernando, Quan Xiao, Yan Xin, Tianyi Chen
arXiv:2604.05087v4 Announce Type: replace
Abstract: Generative large language models (LLMs) are increasingly used as inference-time components in retrieval pipelines, for tasks such as query rewritin...
By Omri Uzan, Ron Polonsky, Douwe Kiela, Christopher Potts
arXiv:2607. 27766v1 Announce Type: cross Abstract: On-device in-context learning (ICL) relies on pre-inference retrieval to select demonstrations for useful context before downstream model inference.
By Xinyu Luo, Hui Liu, Yihua Shao, Junyi Yang, Arindam Basu, Haoliang Li
Telecom question answering (QA) is a challenging setting for retrieval-augmented generation (RAG): evidence is fragmented across standards, papers, encyclopedic resources, and web documents, and answers often hinge on technical tables, equations, and specialized protocol language. In low-resource subdomains, generator fine-tuning can over-specialize and degrade general capability, making query-side retriever adaptation an attractive alternative.
arXiv:2609.15296v1 Announce Type: new
Abstract: Universal multimodal embedding (UME) learns unified representations across modalities, enabling a single model to support diverse retrieval tasks. Rece...
By Mingzhou Jiang, Peixi Wu, Hang Cheng, Yunhao Zhou, Biao Yang, Wei Yuan, Yun Li, Fan Yang, Wenwu Ou, Honghui He
The paper investigates the geometric capacity of vector retrieval systems, focusing on the maximum recall achievable with a fixed document index. It demonstrates that, on real-world benchmarks, single-vector query encoders often underperform relative to the index’s potential. The authors provide theoretical evidence that learning such encoders can be computationally hard, constructing a task where a simple neural network can achieve perfect recall while any statistical-query learner would need exponentially many queries to surpass random chance.
By Anders Wikum, Nina Mishra, Amin Saberi, Tal Wagner
The paper introduces the Generative Embedding Benchmark (GEB), which evaluates how much content from an embedding can be recovered by a decoder that only has access to the frozen embedding and a question, without the original image or intermediate features. GEB uses a curated visual‑question‑answering dataset with 1,800 development and 900 test items covering natural images, scene text, and visual documents. Experiments on seven public embedding models show that visual‑only scores range from 28.25 to 33.21, while joint image‑question encoding boosts scores up to 65.56, revealing that generative readout uncovers information bottlenecks not captured by traditional separability‑based benchmarks.
By Yun Li, Biao Yang, Peixi Wu, Yunhao Zhou, Mingzhou Jiang, Wei Yuan, Fan Yang, Wenwu Ou
The paper introduces AllocEmbed, an allocate‑then‑embed framework that reallocates a fixed visual‑input budget across more video frames to improve retrieval performance. A lightweight allocator uses low‑cost previews to assign frame‑wise resolutions before the embedding backbone, preserving detail where it most benefits retrieval while reducing visual cost elsewhere. Retrieval‑Driven Policy Optimization (RDPO) learns the allocator directly from retrieval feedback, and the method integrates with existing systems without modifying the embedding model.
By Song Jin, Zhongtao Jiang, Chenglei Shen, Huanxuan Liao, Haozhe Chi, Zhiwei Wang, Kun Xu, Yong Liu
arXiv:2609.22100v1 Announce Type: cross
Abstract: Retrieval-augmented generation (RAG) improves language models with retrieved evidence, but processing many long passages is costly and can introduce...
By Artem Sakhno, Grigorii Davydenko, Omar Zoloev, Julia Belikova, Andrey Savchenko, Maksim Makarenko
arXiv:2604. 23336v3 Announce Type: replace-cross Abstract: Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs.
By Teng Chen, Sheng Xu, Feixiang Guo, Xiaoyu Wang, Qingqing Gu, Hongyan Li, Luo Ji