Retrieval-augmented generation

Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.

6,478 stories · RSS feed

arXiv AI

Jul 20

Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching

arXiv:2607. 15516v1 Announce Type: cross Abstract: Production LLM deployments combine two cost-reduction primitives: prompt caching (a discounted rate for re-used token prefixes) and prompt compression (fewer tokens sent).

By Yan Song

llms rag benchmarks

arXiv AI

Jul 20

Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models

arXiv:2601. 22818v2 Announce Type: replace-cross Abstract: Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels.

By Charles Westphal, Keivan Navaie, Fernando E. Rosas

llms rag fine-tuning safety

arXiv AI

Jul 20

NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning

arXiv:2607. 15776v1 Announce Type: new Abstract: OWL ontologies provide a formal knowledge representation framework that enables semantic reasoning, and have been widely adopted across domains such as healthcare and bioinformatics.

By Hui Yang, Jiaoyan Chen, Yiping Song, Renate Schmidt, Wen Zhang

llms rag

arXiv AI

Jul 20

Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning

arXiv:2607. 15388v1 Announce Type: new Abstract: Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help turn wrong candidates into correct ones.

By Chih-Hsuan Yang, Jingyan Jiang, Vikram Vasudevan, Cheng-Hau Yang, Huihuo Zheng, Le Chen, Eliu A. Huerta, Venkatram Vishwanath, Ian T. Foster, Rajeev Thakur

llms rag agents

arXiv AI

Jul 20

Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models

arXiv:2607. 15893v1 Announce Type: cross Abstract: While the internal mechanisms of autoregressive (AR) transformers have been studied extensively, much less is known about diffusion language models (DLMs), an emerging alternative that generates text by iterative denoising.

By Andy Catruna, Emilian Radoi

llms rag diffusion

arXiv Machine Learning

Jul 20

Mixing Configurations for Downstream Prediction

arXiv:2510. 19248v2 Announce Type: replace Abstract: Clustering-based features are widely used in machine learning, but most methods must choose a resolution -- a choice that is global, fixed, and ad hoc.

By Juntang Wang, Hao Wu, Yihan Wang, Dongmian Zou, Shixin Xu

rag

arXiv Machine Learning

Jul 20

Knowledge-Guided Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Label-Conditioned Contrastive Alignment

arXiv:2607. 15928v1 Announce Type: new Abstract: Adult and pediatric electrocardiogram (ECG) interpretation relies on age-sensitive criteria, and models pretrained mainly on adult ECGs often transfer poorly to pediatric populations when pediatric labels are scarce.

By Xinran Liu, Yuwen Li, Hongxiang Gao, Heyang Xu, Jianqing Li, Zongmin Wang, Chengyu Liu

rag fine-tuning multimodal safety

arXiv Machine Learning

Jul 20

E3DGS: Unified Geometric-Photometric Equivariance for 3D Gaussian Splatting via Color-as-Geometry Embedding

arXiv:2607. 15536v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) captures scenes by coupling explicit geometry (position, covariance) with view-dependent photometry (Spherical Harmonics).

By Chankyo Kim, Maani Ghaffari

rag

arXiv AI

Jul 20

AV-JEPA: Extending LeJEPA to Audio-Visual Self-Supervised Learning

arXiv:2607. 15295v1 Announce Type: cross Abstract: We present AV-JEPA, an elegant multimodal extension of LeJEPA to audio-visual self-supervised learning.

By Benjamin Robson, Santeri Mentu, Wenshuai Zhao, Arno Solin

llms rag diffusion computer-vision multimodal safety

arXiv Machine Learning

Jul 20

Bifocal Attention: Harmonizing Geometric and Spectral Positional Embeddings for Algorithmic Generalization

arXiv:2601. 22402v2 Announce Type: replace-cross Abstract: Rotary Positional Embeddings (RoPE) have become the standard for Large Language Models (LLMs) due to their ability to encode relative positions through geometric rotation.

By Kanishk Awadhiya

llms rag robotics

arXiv AI

Jul 20

Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation

arXiv:2508. 09860v2 Announce Type: replace Abstract: Human-aligned AI is a critical component of co-creativity, as it enables models to accurately interpret human intent and generate controllable outputs that align with design goals in collaborative content creation.

By In-Chang Baek, Seoyoung Lee, Sung-Hyun Kim, Geumhwan Hwang, KyungJoong Kim

rag reinforcement-learning

arXiv Machine Learning

Jul 20

Interpretable Role-Based Clustering in Multi-Layer Financial Networks

arXiv:2507. 00600v3 Announce Type: replace-cross Abstract: Understanding the functional roles of financial institutions within interconnected markets is critical for effective supervision, systemic risk assessment, and resolution planning.

By Christian Franssen, Thao Le, Iman van Lelyveld, Bernd Heidergott

rag

arXiv AI

Jul 20

On the Geometry of Learned Representations in Event-Based Multi-Modal Egomotion Estimation

arXiv:2607. 15794v1 Announce Type: cross Abstract: Classical approaches to event-based egomotion estimation, including those adopted by the top-performing teams of the ELOPE challenge, rely on geometric optimization frameworks such as contrast maximization, homography estimation, or dense optical flow combined with analytic motion inversion.

By Stefano Silvestrini, Michele Ceresoli

rag diffusion computer-vision multimodal

arXiv Machine Learning

Jul 20

DELUGE: Towards Continental-Scale Daily Pluvial Flood Damage Prediction via Interpretable Conditioning on Foundation Model Embeddings

arXiv:2607. 16050v1 Announce Type: new Abstract: Pluvial (rainfall-driven) flooding accounts for 45% of National Flood Insurance Program (NFIP) claims in the United States and is harder to predict than its riverine and coastal counterparts, with existing approaches limited to coarse resolution, regional domains, or computationally intensive process-based models unsuitable for daily continental-scale use.

By Yuya Kawakami, Daniel Cayan, Dongyu Liu, Kwan-Liu Ma, Tom Corringham

rag multimodal safety

arXiv Machine Learning

Jul 20

Manifold Dimension Estimation via Local Graph Structure

arXiv:2510. 15141v5 Announce Type: replace-cross Abstract: Most existing manifold dimension estimators rely on the assumption that the underlying manifold is locally flat within the neighborhoods under consideration.

By Zelong Bi, Pierre Lafaye de Micheaux

rag benchmarks

arXiv AI

Jul 20

A Critical Analysis of Trustworthy AI Tools, Mark Frameworks, and the Implementation Chasms

arXiv:2607. 15480v1 Announce Type: new Abstract: As artificial intelligence (AI) systems increasingly impact society, ensuring their ethical and trustworthy deployment has become a global priority.

By Michael Papademas, Xenia Ziouvelou, Kostas Karpouzis, Vangelis Karkaletsis

rag safety

arXiv Machine Learning

Jul 20

Rethinking the Global Knowledge of CLIP in Training-Free Open-Vocabulary Semantic Segmentation

arXiv:2502. 06818v4 Announce Type: replace Abstract: Recent works modify CLIP to perform open-vocabulary semantic segmentation in a training-free manner (TF-OVSS).

By Jingyun Wang, Cilin Yan, Guoliang Kang

rag computer-vision benchmarks

arXiv AI

Jul 20

CAMMAR: Culture-Aware Matryoshka for Metaphorical Arabic Representations

arXiv:2607. 15847v1 Announce Type: cross Abstract: Metaphor in Arabic is a culturally grounded mechanism for constructing meaning, encoding cultural knowledge that shapes interpretation.

By Suzan Awinat, Alfonso Ortega del Puente

llms rag benchmarks

arXiv AI

Jul 20

Ruling Out to Rule In: Contrastive Hypothesis Retrieval for Medical Question Answering

arXiv:2604. 04593v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) grounds large language models in external medical knowledge, yet standard retrievers frequently surface hard negatives that are semantically close to the query but describe clinically distinct conditions.

By Byeolhee Kim, Min-Kyung Kim, Young-Hak Kim, Tae-Joon Jeon

llms rag nlp benchmarks

arXiv Machine Learning

Jul 20

Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraints

arXiv:2607. 16027v1 Announce Type: new Abstract: Introduction: Biological systems face anatomical and metabolic constraints, including costly synaptic maintenance and limited connectivity.

By Patrick Inoue, Florian R\"ohrbein, Andreas Knoblauch

rag efficiency benchmarks

Get the daily briefing