Retrieval-augmented generation

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

6,126 stories · RSS feed

arXiv AI

Oct 7

Massive Activation Gating Channel in Large Language Models

The paper identifies a single input embedding channel, called the massive activation gating channel (MAGC), that controls the emergence of massive activations in large language models. When the MAGC value is sufficiently large or small, the spike feed‑forward network outputs exhibit exceptionally large magnitudes. The authors verify MAGC across six models and provide a theoretical explanation linking the channel to a quadratic form that mixes specific columns of the down‑projection matrix, which produce massive activations.

By Minjia Mao, Shi Chen, Bowen Yin, Xiao Fang

llms rag

arXiv AI

Oct 7

OTel: Open Telco AI Datasets, Benchmarks, and Models

OTel is an open telecom AI resource that provides derived datasets for retrieval, reranking, instruction tuning, and safety/abstention, along with 30 full‑parameter post‑trained baselines covering 10 embedding models, 3 rerankers, and 17 language models. The project has seen significant community engagement, with over 16 million model downloads and more than 157 media mentions by May 2026. Post‑training on OTel data improves performance across all model families, achieving 93.1% NDCG@10 for embeddings, 0.947 MRR@10 for rerankers, and 87.8% correctness for language models.

By Farbod Tavakkoli, Gregory Diamos, Kenneth Church, David Kanter, Mark Austin, Imtiaz Karim, Mirza Masfiqur Rahman, Merouane Abdelkader Debbah, Zeinab Nezami, Ali Maatouk, Leandros Tassiulas, Rex Ying, Nick Sorros, Louis Powell, Nikolaos Vasiloglou, Ashish Vaswani, Somanshu Singla, Adarsh Chaluvaraju

llms rag fine-tuning benchmarks safety

arXiv AI

Oct 7

ShanLiangRen: A Nutrition Agent for Personalized Daily Meal Planning

ShanLiangRen is a nutrition agent designed to generate personalized daily meal plans that satisfy both user constraints and multidimensional nutritional goals. It transforms dietary specifications, nutrient data, user attributes, and natural language requirements into a constrained planning instance, then uses a retrieval‑augmented generation approach to narrow the candidate set from a large ingredient and recipe space. Finally, it refines plans via Pareto‑guided iterative revisions with an LLM, producing fully quantified meal plans with explicit ingredients, portion sizes, and compliance reports.

By Miao Xie, Xiao Zhang, Yuan Wang, Ruixin Zhu, Chunli Lv

llms rag agents

arXiv AI

Oct 7

Quantum Entangled Multimodal Fusion Networks (QEMFN): Resource-Aware Hybrid Vision-Language Fusion via Trainable Entanglement

arXiv:2610.08216v1 Announce Type: new Abstract: Multimodal vision-language systems typically fuse image and text embeddings through classical operators such as concatenation, attention, bilinear pool...

By Srikar Alla, Ali Shiri Sichani, Chi-Ren Shyu

llms rag multimodal benchmarks safety

arXiv AI

Oct 7

Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs

arXiv:2610.06977v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples, especially in black-box settings where only open-sou...

By Xiaojun Jia, Simeng Qin, Yiming Li, Jie Liao, Sensen Gao, Ke Ma, Yang Liu, Xiaochun Cao

llms rag multimodal benchmarks safety

arXiv AI

Oct 7

Aggregating User Preferences while Ensuring Equity, Diversity, and Inclusion using Graph Summarization

arXiv:2610.07128v1 Announce Type: cross Abstract: Aggregating the preferences of diverse user groups into a collective outcome raises fundamental challenges of equity, diversity, and inclusion (EDI):...

By Adji Marieme Sita Ciss\'e, Malek Mouhoub

rag nlp safety

arXiv AI

Oct 7

WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification

arXiv:2610.07384v1 Announce Type: cross Abstract: Individual animal re-identification from camera-trap imagery is an instance retrieval problem central to non-invasive wildlife monitoring: a query im...

By Turhan Can Kargin, Piotr Kubaty, Ekaterina Rostovskaya, Izabela Wierzbowska, Bartosz Zieli\'nski, Marcin Przewi\k{e}\'zlikowski

rag computer-vision fine-tuning benchmarks

arXiv AI

Oct 7

Linear Fitness Subspace in Protein Language Models Enables Sample-Efficient Directed Evolution

arXiv:2610.07607v1 Announce Type: cross Abstract: Model-guided directed evolution seeks to identify high-fitness protein variants under limited oracle budgets. Protein language models (PLMs) provide...

By SiYuan Ma, Canran Xiao, Zikai Xiao, Albert Gao, Liang He, Xuan-Yu Wang, Shuying Cao, Xiaojun Jia

llms rag

arXiv AI

Oct 7

CACHEFORGE: LLM-Guided End-to-End Generative Cache Replacement Policy for Performance and Hardware Efficiency

CACHEFORGE introduces a novel framework that uses a large language model (LLM) to evolve cache‑replacement policies end‑to‑end. In each iteration, the LLM generates new C++ replacement logic, which is evaluated by a trace‑based simulator and refined through reward shaping, structural checks, and mutation. The resulting policies are compact, hardware‑aware, and outperform existing CRC‑2 baselines on SPEC CPU2006, achieving significant improvements in hit rate and IPC across diverse workloads.

By Kaushal Mhapsekar, Bita Aslrousta, Brijesh Kumar Bhayana, Paula Contreras, Azam Ghanbari, Ethan Goodman, Anna Andriiko, Samira Mirbagher Ajorpaz

llms rag

arXiv AI

Oct 7

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

Oct 7

Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering

arXiv:2610.08388v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on kno...

By Yang Hong, Yajun Yang, Xin Wang, Liping Jing, Qinghua Hu

llms rag nlp efficiency benchmarks safety

arXiv AI

Oct 7

Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic Systems

arXiv:2610.08400v1 Announce Type: cross Abstract: Large-scale self-supervised pretraining has reshaped modern machine learning, substantially advancing the ability of language and vision models to ge...

By Kasper Helverskov Petersen, Rasmus Hannibal Tirsgaard, Fran\c{c}ois R J Cornet, Mikkel Jordahn, Mikkel N. Schmidt

rag fine-tuning benchmarks

arXiv AI

Oct 7

DrugMCTS: a drug repurposing framework combining multi-agent, RAG and Monte Carlo Tree Search

arXiv:2507.07426v4 Announce Type: replace Abstract: Recent advances in large language models have demonstrated considerable potential in scientific domains such as drug repositioning. However, their...

By Zerui Yang, Yuwei Wan, Siyu Yan, Yudai Matsuda, Tong Xie, Linqi Song

llms rag agents fine-tuning

arXiv AI

Oct 7

When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction

arXiv:2605.12922v2 Announce Type: replace Abstract: Large language models can follow complex instructions in a single turn, yet over long multi-turn interactions they often lose the thread of instruc...

By Vardhan Dongre, Joseph Hsieh, Viet Dac Lai, Seunghyun Yoon, Trung Bui, Dilek Hakkani-T\"ur

llms rag benchmarks safety

arXiv AI

Oct 7

Qubit-centric Transformer for Surface Code Decoding

arXiv:2510.11593v3 Announce Type: replace-cross Abstract: For reliable large-scale quantum computation, quantum error correction (QEC) is essential to protect logical information distributed across m...

By Seong-Joon Park, Hee-Youl Kwak, Yongjune Kim

llms rag benchmarks

arXiv AI

Oct 7

Recommender system in X inadvertently profiles ideological positions of users

arXiv:2602.02624v2 Announce Type: replace-cross Abstract: Several data protection laws restrict processing that reveals political opinions, irrespective of the controller's intent. Whether recommende...

By Paul Bouchaud, Pedro Ramaciotti

rag

arXiv AI

Oct 7

World Properties without World Models: Distributional Associations and the Interpretation of Decoding Results from Language Models

arXiv:2603.04317v2 Announce Type: replace-cross Abstract: A growing literature shows that variables can be linearly decoded from the activations of large language models (LLMs). These range from prop...

By Elan Barenholtz

llms rag

arXiv AI

Oct 7

Voice "Cloning" is Style Transfer

arXiv:2605.16578v4 Announce Type: replace-cross Abstract: Artificially generated speech is increasingly embedded in everyday life. Voice cloning in particular enables applications where identity pres...

By Kaitlyn Zhou, Federico Bianchi, Martijn Bartelds, Anna Pot, Yongchan Kwon, James Zou

rag

arXiv AI

Oct 7

KadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat

arXiv:2605.18850v2 Announce Type: replace-cross Abstract: We introduce KadiAssistant, a privacy-by-design AI assistant integrated into the Kadi research data ecosystem, enabling researchers to effici...

By Adrian Cierpka, Mohammad Shafiqul Islam, Johannes Steinh\"ulb, Eric Dietriche Sesso Domtchoueng, Michael Selzer, Arnd Koeppe

llms rag agents safety

arXiv Machine Learning

Oct 7

Sample-Optimal Estimation of the Fr\'echet Inception Distance

The paper investigates the sample complexity of estimating the Fréchet Inception Distance (FID) between high‑dimensional Gaussian distributions when one distribution is known. It establishes tight bias and variance bounds for the empirical plug‑in estimator, shows how higher‑order extrapolation reduces bias, and introduces a new Relative Taylor Debiasing (RTD) algorithm that achieves optimal sample complexity. Experiments on synthetic data and ImageNet confirm the theoretical predictions and demonstrate RTD’s superior accuracy with limited samples.

By Ziyun Chen, Jerry Li, Kevin Tian, Yusong Zhu

rag safety

Get the daily briefing