arXiv Machine Learning

Learning Query Encoders Can Be Hard Even When Vector Retrieval Is Geometrically Easy

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.

arXiv Computation and Language

Aug 27

Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrieval

The paper introduces Efficient Retrieval Adapter (ERA), a query‑side adapter framework that enables dense retrieval systems to adapt to asymmetric query–document scenarios without re‑indexing. ERA first aligns the embedding spaces of a powerful query embedder and a lightweight document embedder using unlabeled documents, then fine‑tunes the aligned query representation with a small set of labeled query‑document pairs. In experiments on 126 MAIR retrieval tasks across six domains, ERA boosts average nDCG@10 by up to 8.2 points in symmetric settings and over 12 points in asymmetric settings while requiring far fewer labels than fully supervised adapter training.

By Seiji Maekawa, Moin Aminnaseri, Pouya Pezeshkpour, Estevam Hruschka

rag fine-tuning

arXiv AI

Jun 3

$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval

arXiv:2601. 20844v3 Announce Type: replace-cross Abstract: This paper studies the Minimal Embeddable Dimension (MED): the least dimension in which there exists a configuration of $m$ object vectors so that every subset of size at most $k$ is exactly retrieved by score comparison.

By Zihao Wang, Hang Yin, Lihui Liu, Hanghang Tong, Yangqiu Song, Ginny Wong, Simon See

llms rag

arXiv AI

2d ago

Learning to Retrieve via Reinforcement Learning in Embedding Space

arXiv:2610.07731v1 Announce Type: cross Abstract: Dense retrieval models are typically trained with contrastive objectives that learn effective representations but do not directly optimize retrieval...

By Qi Liu, Fengming Liang, Yiqun Chen, Erhan Zhang, Jiaxin Mao

rag reinforcement-learning benchmarks

arXiv AI

Jun 17

Non-negative Elastic Net Decoding for Information Retrieval

arXiv:2606. 17910v1 Announce Type: cross Abstract: Dense retrieval has become the dominant paradigm in information retrieval, in which each document is scored against a query by the inner product of their vector embeddings, and the top-$k$ documents by score are retrieved for this query.

By Koki Okajima, Yasutoshi Ida, Tsukasa Yoshida, Yasuaki Nakamura

rag benchmarks

arXiv AI

Aug 19

DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval

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

llms rag benchmarks

arXiv Machine Learning

Jun 4

Distributional Approximate Nearest Neighbour Search for Uncertainty-Aware Retrieval

arXiv:2606. 04603v1 Announce Type: cross Abstract: Approximate Nearest Neighbour search indices form the backbone of real-world recommender systems, enabling real-time candidate retrieval over million-item catalogues.

By Olivier Jeunen

rag diffusion

arXiv Machine Learning

Jul 14

Retrieval with Multiple Query Vectors through Anomalous Pattern Detection

arXiv:2605. 01965v2 Announce Type: replace Abstract: A classical vector retrieval problem typically considers a \emph{single} query embedding vector as input and retrieves the most similar embedding vectors from a vector database.

By Allassan Tchangmena A Nken, Baimam Boukar Jean Jacques, Miriam Rateike, Celia Cintas, Skyler Speakman

rag

arXiv Computation and Language

1d ago

Document Optimization for Black-Box Retrieval via Reinforcement Learning

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

llms rag reinforcement-learning multimodal

arXiv AI

Jun 3

Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors

arXiv:2606. 02814v1 Announce Type: cross Abstract: Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs.

By Francisco Valentini, Edgar Altszyler, Martin Fajcik

llms rag benchmarks safety

arXiv Computation and Language

1d ago

Finding the Right Balance: Relevance and Diversity in LLM Retrieval

arXiv:2610.09412v1 Announce Type: cross Abstract: Retrieval diversification is widely available in retrieval-augmented generation (RAG) frameworks, yet prior studies disagree on whether it improves r...

By Guillaume Brouillette (Universit\'e du Qu\'ebec \`a Trois-Rivi\`eres, Trois-Rivi\`eres, Canada), Faustin Kagabo (Universit\'e du Qu\'ebec \`a Trois-Rivi\`eres, Trois-Rivi\`eres, Canada), Usef Faghihi (Universit\'e du Qu\'ebec \`a Trois-Rivi\`eres, Trois-Rivi\`eres, Canada), Nadia Ghazzali (Universit\'e du Qu\'ebec \`a Trois-Rivi\`eres, Trois-Rivi\`eres, Canada)

llms rag

arXiv Machine Learning

Jun 15

Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA

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

llms rag robotics efficiency benchmarks

arXiv AI

Sep 3

ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering

ViSAR is a training‑free, adaptive‑k retrieval method for Visual Document Question Answering that operates directly in the embedding space to build a query‑conditioned page‑level similarity matrix. By dynamically selecting the number of pages to retrieve based on query relevance, ViSAR reduces Retrieval‑Augmented Generation latency by up to 58.7% while maintaining or improving answer accuracy across multiple encoders and Large Vision‑Language Models. The structure of the similarity matrix also correlates with answer accuracy, indicating potential for retrieval quality‑aware document understanding.

By Adrien Mialland, Marc Plantevit, Julien Gallois, C\'eline Robardet

llms rag nlp multimodal

Related stories