Retrieval-augmented generation

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

6,643 stories · RSS feed

arXiv AI

Jun 9

TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks

arXiv:2510. 16028v4 Announce Type: replace-cross Abstract: Neural networks increasingly run on hardware outside the user's control (cloud GPUs, inference marketplaces).

By Jianzhu Yao, Hongxu Su, Taobo Liao, Zerui Cheng, Huan Zhang, Xuechao Wang, Pramod Viswanath

llms rag diffusion efficiency safety

arXiv AI

Jun 9

From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG

arXiv:2603. 03292v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields.

By Wenhao Wu, Zhentao Tang, Yafu Li, Shixiong Kai, Mingxuan Yuan, Zhenhong Sun, Chunlin Chen, Zhi Wang

llms rag agents reinforcement-learning benchmarks safety

arXiv AI

Jun 9

AgentTrust: A Self-Improving Trust Layer for AI-Agent Actions

arXiv:2606. 08539v1 Announce Type: new Abstract: AI agents increasingly take consequential actions -- shell commands, cloud operations, and arbitrary tool-calls -- so a trust layer must decide, per action, whether to allow, warn, block, or escalate.

By Chenglin Yang

llms rag agents

arXiv Machine Learning

Jun 9

The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection

arXiv:2606. 09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedded in retrieved documents backfire against the attacker, suppressing the target brand below the injection-free baseline.

By Hyunseok Paeng

llms rag safety

arXiv AI

Jun 9

Performative Learning Theory

arXiv:2602. 04402v3 Announce Type: replace-cross Abstract: Performative predictions influence the very outcomes they aim to forecast.

By Julian Rodemann, Unai Fischer-Abaigar, James Bailie, Krikamol Muandet

rag

arXiv AI

Jun 9

GraphLoRA: Structure-Aware Low-Rank Adaptation for Large Language Model Recommendation

arXiv:2606. 07526v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong potential for recommendation (LLMRec) due to their powerful reasoning and generalization abilities.

By Lin Mu, Guoji Wang, Li Ni, Lei Sang, Zhize Wu, Peiquan Jin, Yiwen Zhang

llms rag benchmarks

arXiv AI

Jun 9

Phantom transitions in language model fine-tuning

arXiv:2606. 07559v1 Announce Type: cross Abstract: Fine-tuning a language model on contexts whose correct completion has a near-synonym competitor often fails silently.

By Vaibhav Prakash, Jayasri Dontabhaktuni

llms rag fine-tuning

arXiv Machine Learning

Jun 9

Entropic Optimal Transport Eigenmaps for Nonlinear Alignment and Joint Embedding of High-Dimensional Datasets

arXiv:2407. 01718v2 Announce Type: replace-cross Abstract: Embedding high-dimensional data into a low-dimensional space is an indispensable component of data analysis.

By Boris Landa, Yuval Kluger, Rong Ma

rag diffusion safety

arXiv AI

Jun 9

OSMGraphCLIP: Learning Global Location Representations from OpenStreetMap Graphs

arXiv:2606. 08046v1 Announce Type: new Abstract: We present OSMGraphCLIP, a CLIP-style geospatial representation model that learns global location embeddings from freely available OpenStreetMap (OSM) data.

By Dimitrios Michail, Eleni Saka, Ioannis Giannopoulos, Ioannis Papoutsis

rag benchmarks safety

arXiv AI

Jun 9

Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents

arXiv:2606. 09316v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enables agents to access external knowledge at inference time, but it primarily retrieves fragmented declarative evidence, leaving agents to repeatedly infer task procedures from passages, manuals, examples, logs, or trajectories.

By Qianjun Pan, Yutao Yang, Junsong Li, Jie Zhou, Kai Chen, Xin Li, Qin Chen, Liang He

rag agents

arXiv Machine Learning

Jun 9

Advancing Ligand-based Virtual Screening and Molecular Generation with Pretrained Molecular Embedding Distance

arXiv:2604. 24474v2 Announce Type: replace Abstract: Molecular similarity plays a central role in ligand-based drug discovery, such as virtual screening, analog searching, and goal-directed molecular generation.

By Shiyun Wa, Yifei Wang, Simone Sciabola, Ye Wang

rag

arXiv AI

Jun 9

When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference

arXiv:2606. 08098v1 Announce Type: new Abstract: Majority voting over sampled answers is the dominant unsupervised aggregator for multi-sample LLM inference.

By Yasushi Sakai, Allen Song, Kent Larson

llms rag benchmarks

arXiv AI

Jun 9

Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering

arXiv:2602. 17911v3 Announce Type: replace-cross Abstract: Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is inherently conditional: nearly every decision depends on patient-specific factors such as comorbidities and contraindications.

By Jash Rajesh Parekh, Wonbin Kweon, Joey Chan, Rezarta Islamaj, Robert Leaman, Pengcheng Jiang, Chih-Hsuan Wei, Zhizheng Wang, Zhiyong Lu, Jiawei Han

rag nlp benchmarks

arXiv Machine Learning

Jun 9

Integrating gene regulatory priors into Transformer attention with scTransformer for interpretable scRNA-seq analysis

arXiv:2606. 09558v1 Announce Type: cross Abstract: Motivation: Transformer-based models are increasingly applied to large-scale single-cell transcriptomics, showing strong performance through self-supervised learning on millions of cells.

By Mikele Milia, Louis Fabrice Tshimanga, Henning Mueller, Manfredo Atzori, Barbara Di Camillo

llms rag safety

arXiv AI

Jun 9

HARP: Efficient Data Selection for Finetuning Large Language Models

arXiv:2606. 07690v1 Announce Type: cross Abstract: Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repeatedly finetuning models.

By Ning Wang, Zhengxin Zhang, Maosen Tang, Yitang Gao, Claire Cardie, Sainyam Galhotra

llms rag fine-tuning efficiency safety

arXiv AI

Jun 9

OnlyDense: Reduced-Order Modeling for Lagrangian simulation

arXiv:2606. 09065v1 Announce Type: cross Abstract: In science and engineering, Lagrangian simulation methods such as Smooth Particle Hydrodynamics (SPH) or Material Point Method (MPM) are often employed to study the behavior of dynamic systems.

By Tu Do, Shannon Ryan, Santu Rana

rag diffusion

arXiv Machine Learning

Jun 9

Observation-driven correction of numerical weather prediction for marine winds

arXiv:2512. 03606v2 Announce Type: replace Abstract: Accurate marine wind forecasts are essential for safe navigation, ship routing, and energy operations, yet they remain challenging because observations over the ocean are sparse, heterogeneous, and temporally variable.

By Matteo Peduto, Qidong Yang, Jonathan Giezendanner, Devis Tuia, Sherrie Wang

llms rag

arXiv Machine Learning

Jun 9

A Unified Structured Query Understanding Framework for Industrial Semantic Search

arXiv:2605. 27441v2 Announce Type: replace-cross Abstract: Query understanding in large-scale industrial search systems is typically implemented as a cascade of disparate, task-specific components.

By Ping Liu, Qianqi Shen, Jianqiang Shen, Chunnan Yao, Kevin Kao, Rajat Arora, Dan Xu, Baofen Zheng, Yunxiang Ren, Benjamin Le, Ali Hooshmand, Igor Lapchuk, Juan Bottaro, Raghavan Muthuregunathan, Caleb Johnson, Liangjie Hong, Jingwei Wu, Wenjing Zhang

llms rag efficiency

arXiv AI

Jun 9

NeuroAlign: Hierarchical Multimodal Fusion of Dynamic and Structural Neuroimaging for MCI Analysis

arXiv:2606. 07635v1 Announce Type: cross Abstract: Multimodal neuroimaging fusion of functional MRI (fMRI) and diffusion tensor imaging (DTI) provides complementary information for cognitive impairment analysis, but remains challenged by heterogeneous feature spaces and misaligned representations.

By Xiongri Shen, Zhenxi Song, Jiaqi wang, Yi Zhong, Leilei Zhao, Chenqi Xu, Linling Li, Yichen Wei, Lingyan Liang, Demao Deng, Luping Song, Ping Luan, Ahmed M. Anter, Shuqiang Wang, Baiying Lei, Zhiguo Zhang

rag diffusion multimodal safety

arXiv AI

Jun 9

Cheap Reward Hacking Detection

arXiv:2606. 08893v1 Announce Type: cross Abstract: A small transformer encoder is trained to map Terminal-Wrench trajectories onto a unit sphere where embedding distance approximates the $L_1$ distance between reward and metadata signals.

By Iv\'an Belenky, Joaqu\'in Itria, Steven Johns

llms rag

Get the daily briefing