Retrieval-augmented generation

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

3,469 stories · RSS feed

arXiv Machine Learning

Jun 11

Measuring Semantic Progress in Multi-turn Dialogue via Information Gain

arXiv:2606. 12332v1 Announce Type: cross Abstract: Evaluating multi-turn dialogue is challenging because quality emerges across turns rather than within individual responses.

By Paul He, Shiva Kasiviswanathan, Dominik Janzing

llms rag safety

arXiv AI

Jun 11

Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

arXiv:2606. 11762v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential.

By Min Sen Tan, Zachary Kit Chun Choy, Syed Ali Redha Alsagoff, Nadya Yuki Wangsajaya, Mohor Banerjee, Swaagat Bikash Saikia, Alvin Chan

llms rag agents benchmarks

arXiv AI

Jun 11

When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines

arXiv:2606. 11265v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate downstream model outputs through malicious knowledge injection.

By Xi Nie, Hongwei Li, Shenghao Wu, Mingxuan Li, Jiachen Li, Wenbo Jiang

rag benchmarks safety

arXiv AI

Jun 11

Carbon-Aware Governance Gates: An Architecture for Sustainable GenAI Development

arXiv:2602. 19718v2 Announce Type: replace-cross Abstract: The rapid adoption of Generative AI (GenAI) in the software development life cycle (SDLC) increases computational demand, which can raise the carbon footprint of development activities.

By Mateen A. Abbasi, Tommi J. Mikkonen, Petri J. Ihantola, Muhammad Waseem, Pekka Abrahamsson, Niko K. M\"akitalo

rag agents

arXiv Machine Learning

Jun 11

MLT-Dedup: Efficient Large-Scale Online Video Deduplication via Multi-Level Representations and Spatial-Temporal Matching

arXiv:2606. 12215v1 Announce Type: cross Abstract: The explosive growth of user-generated video content on online platforms is accompanied by the emergence of numerous near-duplicate videos--videos that are identical or highly similar but differ by partial edits.

By David Yuchen Wang, Haoying Li, Hailun Xu, Wei Chee Yew, Zirui Zhu, Sanjay Saha, Hao Hei, Kanchan Sarkar, Kun Xu

rag

arXiv Machine Learning

Jun 11

RePAIR: Predictive Self-Supervised Representation Learning in Chess

arXiv:2606. 11860v1 Announce Type: new Abstract: In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation learning architecture that synthesizes Masked Autoencoders (MAE), Joint Embedding Predictive Architectures (JEPA), and Bidirectional Encoder Representations from Transformers (BERT).

By Christoph Koller, Johannes F\"urnkranz, Timo Bertram

llms rag diffusion reinforcement-learning

arXiv AI

Jun 11

ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning

arXiv:2603. 22934v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves large language model applications by grounding generation in retrieved evidence, but also introduces corpus poisoning as a new attack surface.

By Xiangyu Yin, Yi Qi, Chih-Hong Cheng

llms rag

arXiv AI

Jun 11

Compiler-First State Space Duality and Portable $O(1)$ Autoregressive Caching for Inference

arXiv:2603. 09555v2 Announce Type: replace-cross Abstract: High-throughput Mamba-2 inference is usually tied to fused CUDA and Triton kernels, limiting portability across accelerator backends.

By Cosmo Santoni, Anmol Thapar

rag efficiency

arXiv AI

Jun 11

Augmenting Molecular Language Models with Local $n$-gram Memory

arXiv:2606. 12113v1 Announce Type: cross Abstract: Transformer-based language models for SMILES strings suffer from a locality gap: standard character-level tokenization fragments chemically meaningful motifs, forcing models to repeatedly learn local syntax at the expense of long-range dependencies.

By Xinni Zhang, Zijing Liu, He Cao, Yu Li, Irwin King

llms rag nlp safety

arXiv Machine Learning

Jun 11

Learning Patterns and Abstractions from Perceptual Sequences

arXiv:2503. 10973v2 Announce Type: replace Abstract: Cognition swiftly breaks high-dimensional sensory streams into familiar parts and uncovers their relations.

By Shuchen Wu

llms rag

arXiv Machine Learning

Jun 11

Integral Formulation of QENDy for Robust Nonlinear System Identification

arXiv:2606. 11629v1 Announce Type: cross Abstract: This manuscript proposes an integral formulation of the newly defined quadratic embedding method for identifying nonlinear systems (QENDy).

By Nikhil Saran, Sushant Pokhriyal, Stefan Klus, Rushikesh Kamalapurkar, Joel A. Rosenfeld

rag

arXiv AI

Jun 11

Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions

arXiv:2606. 11828v1 Announce Type: cross Abstract: Audio watermarking aims to embed identifiable information into audio while remaining imperceptible.

By Haiyun Li, Shuhai Peng, Zhisheng Zhang, Jingran Xie, Xiaofeng Xie, Hanyang Peng, Zhiyong Wu

rag

arXiv AI

Jun 11

Semantic search for 100M+ galaxy images using AI-generated captions

arXiv:2512. 11982v2 Announce Type: replace-cross Abstract: Finding scientifically interesting phenomena through slow manual labeling campaigns severely limits our ability to explore the billions of galaxy images produced by telescopes.

By Nolan Koblischke, Liam Parker, Francois Lanusse, Jo Bovy, Irina Espejo, Shirley Ho

llms rag multimodal benchmarks

arXiv AI

Jun 11

Diffusion-based Cumulative Adversarial Purification for Vision Language Models

arXiv:2506. 03933v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications.

By Jia Fu, Yongtao Wu, Yihang Chen, Kunyu Peng, Xiao Zhang, Volkan Cevher, Sepideh Pashami, Anders Holst

llms rag diffusion multimodal safety

arXiv AI

Jun 11

NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track

arXiv:2606. 11199v1 Announce Type: cross Abstract: We present NightFeats, a structured multi-agent retrieval-augmented generation (RAG) system submitted to the MMU-RAGent competition at NeurIPS 2025, where it was awarded Best Dynamic Evaluation in the text-to-text track.

By Quentin Fever, Naziha Aslam

llms rag agents benchmarks

arXiv AI

Jun 11

T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking

arXiv:2606. 11698v1 Announce Type: cross Abstract: Model watermarking safeguards AI model intellectual property by embedding distinctive knowledge that induces unique behavioral signatures.

By Jian-Ping Mei, Weibin Zhang, Ao Yao, Tiantian Zhu, Jie Xiao

rag fine-tuning

arXiv AI

Jun 11

Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction

arXiv:2510. 22335v2 Announce Type: replace-cross Abstract: Reconstructing visual stimuli from fMRI signals is a central challenge bridging machine learning and neuroscience.

By Xu Zhang, Ruijie Quan, Wenguan Wang, Yi Yang

rag diffusion safety

arXiv AI

Jun 11

From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning

arXiv:2606. 11195v1 Announce Type: cross Abstract: Large language models (LLMs) have transformed how humans access information, but not how we reason with it.

By Rikard Rosenbacke, Carl Rosenbacke, Victor Rosenbacke, Martin McKee

llms rag safety

arXiv AI

Jun 11

The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content

arXiv:2606. 11198v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its semantic relevance -- can independently distort the model's attention distribution.

By Yuqi Zhang, Di Zhang

llms rag benchmarks safety

arXiv AI

Jun 11

MSUE: Multi-Modal Soccer Understanding Expert

arXiv:2606. 12106v1 Announce Type: cross Abstract: This paper presents our solution to the 2026 SoccerNet VQA Challenge.

By Litao Li, Yibo Yu, Yufeng Hu, Zhuo Yang, Jiali Wen, Yixin Chen, Yixi Zhou

llms rag nlp fine-tuning multimodal benchmarks

Get the daily briefing