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 3

vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models

arXiv:2603. 04444v3 Announce Type: replace-cross Abstract: As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing -- selecting the right model for each query at inference time -- has become a critical systems challenge.

By Xunzhuo Liu (Steve), Huamin Chen (Steve), Samzong Lu (Steve), Yossi Ovadia (Steve), Guohong Wen (Steve), Hao Wu (Steve), Zhengda Tan (Steve), Jintao Zhang (Steve), Senan Zedan (Steve), Yehudit Kerido (Steve), Liav Weiss (Steve), Haichen Zhang (Steve), Bishen Yu (Steve), Asaad Balum (Steve), Noa Limoy (Steve), Abdallah Samara (Steve), Baofa Fan (Steve), Brent Salisbury (Steve), Ryan Cook (Steve), Zhijie Wang (Steve), Qiping Pan (Steve), Rehan Khan (Steve), Avishek Goswami (Steve), Houston H. Zhang (Steve), Shuyi Wang (Steve), Ziang Tang (Steve), Fang Han (Steve), Zohaib Hassan (Steve), Jianqiao Zheng (Steve), Avinash Changrani (Steve), Xue (Steve), Liu, Bowei He

llms rag agents safety

arXiv AI

Jun 3

Inference Cost Attacks for Retrieval-Augmented Large Language Models

arXiv:2606. 02643v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG)-enhanced LLM systems, while powerful, introduce substantial inference costs due to the inclusion of an extra multi-stage pipeline that dynamically retrieves and synthesizes information from external knowledge sources.

By Chengliang Liu, Liangbo Ning, Yujuan Ding, Wenqi Fan

llms rag agents reinforcement-learning robotics safety

arXiv AI

Jun 3

Attention Calibration for Position-Fair Dense Information Retrieval

arXiv:2606. 02737v1 Announce Type: cross Abstract: Dense retrieval models exhibit positional bias: retrieval effectiveness degrades when relevant information appears later in a passage (Zeng et al.

By Andrianos Michail, Elias Schuhmacher, Juri Opitz, Simon Clematide, Rico Sennrich

llms rag safety

arXiv Machine Learning

Jun 3

TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer

arXiv:2506. 00431v2 Announce Type: replace Abstract: Due to the proficiency of self-attention mechanisms (SAMs) in capturing dependencies in sequence modeling, several existing dynamic graph neural networks (DGNNs) utilize Transformer architectures with various encoding designs to capture sequential evolutions of dynamic graphs.

By Jie Peng, Zhewei Wei, Yuhang Ye

llms rag benchmarks safety

arXiv AI

Jun 3

From Prompt to Service: An SLM-Based Agent Orchestration Gateway for AI-Driven Virtual Worlds

arXiv:2606. 03557v1 Announce Type: new Abstract: As generative AI capabilities expand, AI-driven virtual worlds face a growing architectural challenge.

By Louis Nisiotis, Aimilios Hadjiliasi

rag agents fine-tuning multimodal

arXiv Machine Learning

Jun 3

GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations

arXiv:2606. 03180v1 Announce Type: cross Abstract: Vision-language models (VLMs) for radiology have emerged as a scalable paradigm by leveraging image-report pairs naturally produced in clinical workflows.

By Jonggwon Park, Seongeun Lee, Junhyun Park, Hannah Yun, Hyunwoong Kim, Sohyun Jeong, Hyewon Kang, Byungmu Yoon, Kyoyun Choi

llms rag computer-vision efficiency multimodal safety

arXiv Machine Learning

Jun 3

Reconstructing Content with Collaborative Attention for Universal Multimodal Representation Learning

arXiv:2603. 01471v3 Announce Type: replace-cross Abstract: Multimodal embedding models, rooted in multimodal large language models (MLLMs), have yielded significant performance improvements across diverse tasks such as retrieval and classification.

By Jiahan Chen, Da Li, Hengran Zhang, Yinqiong Cai, Lixin Su, Jiafeng Guo, Daiting Shi, Dawei Yin, Keping Bi

llms rag multimodal

arXiv Machine Learning

Jun 3

The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit

arXiv:2501. 02173v2 Announce Type: replace-cross Abstract: The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance between computational efficiency and predictive accuracy.

By Huixue Zhou, Hengrui Gu, Xi Liu, Kaixiong Zhou, Mingfu Liang, Yongkang Xiao, Srinivas Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen

llms rag

arXiv AI

Jun 3

UR$^2$: Unify RAG and Reasoning through Reinforcement Learning

arXiv:2508. 06165v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown strong capabilities through two complementary paradigms: Retrieval-Augmented Generation (RAG) for knowledge grounding and Reinforcement Learning from Verifiable Rewards (RLVR) for complex reasoning.

By Weitao Li, Boran Xiang, Xiaolong Wang, Zhinan Gou, Weizhi Ma, Yang Liu

llms rag reinforcement-learning benchmarks

arXiv AI

Jun 3

A Robust and Explainable Transformer-Based Framework for Phishing Email Detection

arXiv:2511. 12085v3 Announce Type: replace-cross Abstract: Phishing and related cyber threats are becoming increasingly sophisticated, with email-based phishing remaining the most persistent attack vector.

By Sajad U P

llms rag safety

arXiv Machine Learning

Jun 3

Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models

arXiv:2606. 03780v1 Announce Type: cross Abstract: Causal tracing of factual recall has been studied predominantly in dense transformer language models, where interventions localize information flow to layers or feed-forward modules.

By Yuetian Lu, Ali Modarressi, Yihong Liu, Hinrich Sch\"utze

llms rag

arXiv AI

Jun 3

RGMem: Renormalization Group-inspired Memory Evolution for Language Agents

arXiv:2510. 16392v3 Announce Type: replace Abstract: Personalized and continuous interactions are critical for LLM-based conversational agents, yet finite context windows and static parametric memory hinder the modeling of long-term, cross-session user states.

By Ao Tian, Yunfeng Lu, Xinxin Fan, Changhao Wang, Lanzhi Zhou, Yeyao Zhang, Yanfang Liu

llms rag agents nlp benchmarks

arXiv AI

Jun 3

Non-Identical Diffusion Models in MIMO-OFDM Channel Generation

arXiv:2509. 01641v3 Announce Type: replace-cross Abstract: We propose a novel diffusion model, termed the non-identical diffusion model, and investigate its application to wireless orthogonal frequency division multiplexing (OFDM) channel generation.

By Yuzhi Yang, Omar Alhussein, M\'erouane Debbah

rag diffusion

arXiv Machine Learning

Jun 3

scBatchProx: Federated-Inspired Refinement for Stable Cell-Type Discriminability under Heterogeneous Batch Compositions

arXiv:2602. 00423v3 Announce Type: replace Abstract: Single-cell integration workflows often construct low-dimensional cell embeddings and then refine them with post-hoc methods to reduce batch effects.

By Quang-Huy Nguyen, Jiaqi Wang, Wei-Shinn Ku

rag

arXiv Machine Learning

Jun 3

The Impact of Temporal Granularity on Socio-Demographic Inference from Household Load Profiles

arXiv:2606. 03358v1 Announce Type: new Abstract: Smart meter data can reveal sensitive socio-demographic characteristics of households, raising privacy concerns.

By Dejan Radovanovic, Maximilian Schirl, Andreas Unterweger, G\"unther Eibl

rag safety

arXiv AI

Jun 3

ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models

arXiv:2510. 09711v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches.

By Wenbin Guo, Xin Wang, Jiaoyan Chen, Lingbing Guo, Zhao Li, Zirui Chen

llms rag nlp efficiency benchmarks

arXiv Machine Learning

Jun 3

Spherical Flows for Sampling Categorical Data

arXiv:2605. 05629v3 Announce Type: replace-cross Abstract: We study the problem of learning generative models for discrete sequences in a continuous embedding space.

By Jannis Chemseddine, Gregor Kornhardt, Gabriele Steidl

rag

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 AI

Jun 3

Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals

arXiv:2606. 02631v1 Announce Type: cross Abstract: This paper studies whether audio, images, and video can share a common wavelet token schema rather than relying on separate modality-specific latent grids.

By Shenghao Ding

rag nlp

arXiv Machine Learning

Jun 3

Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification

arXiv:2606. 03292v1 Announce Type: cross Abstract: Many systems used in real-world environments require adding new categories and incorporating new information without forgetting what was previously learnt by the classification model.

By Pablo Garc\'ia-Santaclara, Bruno Fern\'andez-Castro, Rebeca Pilar D\'iaz-Redondo

rag benchmarks

Get the daily briefing