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 22

A Controlled Study of Attention-Only Transformers

arXiv:2607. 18363v1 Announce Type: cross Abstract: Feed-forward networks hold two thirds of a transformer's non-embedding parameters, yet the architecture has not received a necessity test that controls parameters, compute, and depth at once.

By Henry Ndubuaku, Karen Mosoyan, Jakub Mroz, Noah Cylich, Satyajit Kumar, Parkirat Sandhu, Roman Shemet, Justin H Lee

llms rag

arXiv AI

Jul 22

Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures

arXiv:2509. 25045v3 Announce Type: replace-cross Abstract: Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations.

By Marco Bronzini, Carlo Nicolini, Bruno Lepri, Jacopo Staiano, Andrea Passerini

llms rag efficiency safety

arXiv AI

Jul 22

Decoupled Pipeline with Proposal Reranking and Score Fusion for Positive-Unlabeled Marine Species Detection

arXiv:2607. 18700v1 Announce Type: cross Abstract: The FathomNetCLEF 2026 competition combines underwater object detection and fine-grained marine species classification under a positive-unlabeled evaluation setting.

By Robert James Brock, Sebastian Maximilian Krupa, Jason Kahei Tam

rag computer-vision fine-tuning benchmarks

arXiv Machine Learning

Jul 22

Decafs: Disentangled Conditional adversarial Flows

arXiv:2607. 18755v1 Announce Type: new Abstract: Flow-based models have established state-of-the-art performance in generative modeling across domains, but are hard to interpret due to their complex latent embeddings.

By Anirudh jain, Sakshi Varshney, Samuel Kaski, Vikas Garg

rag diffusion benchmarks safety

arXiv Machine Learning

Jul 22

A Better Start for Language Models: Domain-Conditional Position Offsets

arXiv:2607. 18302v1 Announce Type: new Abstract: Autoregressive language models are least accurate at the beginning of a sequence, where little context forces reliance on a generic pretraining prior.

By Ye Qiao

llms rag fine-tuning safety

arXiv AI

Jul 22

LinguistAgent Technical Report: A Reflective Multi-Model Platform for Automated Linguistic Annotation

arXiv:2602. 05493v2 Announce Type: replace-cross Abstract: Data annotation remains a significant bottleneck in the field of humanities and social sciences, particularly for complex linguistic tasks such as metaphor identification.

By Bingru Li

llms rag fine-tuning

arXiv AI

Jul 22

Attacking Graph Foundation Models Through Their Shared Representation

arXiv:2607. 18567v1 Announce Type: new Abstract: A graph foundation model generalizes across graph domains by mapping every input into one shared representation before any task reasoning.

By Pankaj Kumar, Subhankar Mishra

rag nlp safety

arXiv Machine Learning

Jul 22

Reinforcement Learning for Delivery Drone-Based Participatory Sensing in Dynamic Environments

arXiv:2607. 18874v1 Announce Type: new Abstract: Using Unmanned Aerial Vehicle (UAV) for urban sensing has emerged as a powerful paradigm to monitor the status of the city, e.

By Xin Ouyang, Songxin Lei, Xusen Guo, Yutian Jiang, Sijie Ruan, Yuxuan Liang

rag reinforcement-learning robotics

arXiv AI

Jul 22

Physics-Guided Masked Multi-Task Network for Edge-Friendly Battery Health Diagnostics from Sto-chastically Fragmented Charging Profiles

arXiv:2607. 18330v1 Announce Type: cross Abstract: The deployment of reliable lithium-ion battery management systems is crucial for accelerating electrification, yet the joint prognosis of State of Health (SOH) and Remaining Useful Life (RUL) remains severely hindered by task heteroscedasticity.

By Shuhao Chen, Tianyu Shi, Chengyi Tu

llms rag benchmarks

arXiv AI

Jul 22

SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring

arXiv:2607. 18665v1 Announce Type: new Abstract: Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance.

By Chunxiao Li, Yuan Xiong, Lijun Li, Tianyi Du, Wenlong Zhang, Lei Bai, Jing Shao

llms rag agents benchmarks safety

arXiv AI

Jul 22

Trajectory-Aware Clinical Risk Prediction via Severity-Grounded Knowledge Graphs and Retrieval-Augmented Generation

arXiv:2607. 18270v1 Announce Type: new Abstract: While Electronic Health Records (EHRs) offer a wealth of clinical data, effectively augmenting a patient's records with heterogeneous external knowledge to predict the patient's clinical risk remains a significant challenge.

By Kyunghoon Jeon, Youmin Ko, Woohwan Jung, Hyunjoon Kim

rag efficiency benchmarks

arXiv Machine Learning

Jul 22

Beyond Content: Behavioral Policies Reveal Actors in Information Operations

arXiv:2602. 02838v2 Announce Type: replace-cross Abstract: The detection of online influence operations -- coordinated campaigns by malicious actors to spread narratives -- has traditionally depended on content analysis or network features.

By Philipp J. Schneider, Lanqin Yuan, Marian-Andrei Rizoiu

rag robotics

arXiv Machine Learning

Jul 22

Finite-Agent Stochastic Differential Games on Large Graphs: II. Graph-Based Architectures

arXiv:2509. 12484v2 Announce Type: replace Abstract: We propose a novel neural network architecture, called Non-Trainable Modification (NTM), for computing Nash equilibria in stochastic differential games (SDGs) on graphs.

By Ruimeng Hu, Jihao Long, Haosheng Zhou

rag agents robotics benchmarks safety

arXiv Machine Learning

Jul 22

AHEAD: Advancing Multi-Class Label Aggregation with Interpretable Cross-Annotator Modeling

arXiv:2607. 18465v1 Announce Type: new Abstract: Crowdsourced labeling provides valuable labeled data for domains across natural language processing, computer vision, and video.

By Ju Chen, Sijia Xu, Jun Feng, Zhiqiang Gao, Zhengyi Yang

rag computer-vision nlp

arXiv AI

Jul 22

Supra Cognitive Modes: A Routed Architecture for Agent Memory

arXiv:2607. 19096v1 Announce Type: new Abstract: Agent-memory workloads mix direct factual lookup, relation-chain and current-state reasoning, and broad synthesis over long histories.

By Joshua Tobkin, David Yang

rag agents benchmarks safety

arXiv AI

Jul 22

Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models

arXiv:2607. 18695v1 Announce Type: cross Abstract: A popular route to interpretable zero-shot classification asks a large language model (LLM) to describe each class name and prompts CLIP with the resulting descriptors.

By Gautam Rajendrakumar Gare, Jia Shi, Zhiqiu Lin, Deepak Pathak, John Galeotti, Deva Ramanan

llms rag multimodal

arXiv AI

Jul 22

State Compression in Two-Agent LLM Relays: A Closed-World Study of Constraint Preservation

arXiv:2607. 18265v1 Announce Type: new Abstract: Long-running Large Language Model (LLM)-based agents often accumulate large intermediate traces containing audits, eliminations, and numeric calculations.

By Anantha Sharma, Sheeba Elizabeth John, Kaarthik Senthil Kumar, Saratsuhas Vijayababu

llms rag agents nlp efficiency

arXiv Machine Learning

Jul 22

On the Diverse Dynamical Behaviors Arising in Deep Linear Transformers

arXiv:2607. 18584v1 Announce Type: new Abstract: We study the inference-time behavior of deep linear encoder-only transformers through the lens of interacting particle systems.

By Sixu Li, Thomas Jacob Maranzatto, Jan Peszek, Trevor Teolis, Semih Akkoc, Konstantin Riedl, Sennur Ulukus, Nicol\'as Garc\'ia Trillos

llms rag

arXiv AI

Jul 22

Enhancing Transformer-based Routing by Encoding Distance via Relative Positional Encoding

arXiv:2607. 18909v1 Announce Type: new Abstract: This paper explores Relative Positional Encoding (RPE) as an additive bias in Transformer architectures to solve the Team Orienteering Problem.

By Leyre Enc\'io, Daniel Fuertes, Carlos R. del-Blanco, Fernando Jaureguizar

llms rag benchmarks safety

arXiv AI

Jul 22

Memo2496: Expert-Annotated Dataset and Dual-view Adaptive Framework for Music Emotion Recognition

arXiv:2512. 13998v3 Announce Type: replace-cross Abstract: Music Emotion Recognition (MER) is constrained by limited expert annotations and the need to establish robustness across heterogeneous corpora.

By Qilin Li, C. L. Philip Chen, Tong Zhang

rag

Get the daily briefing