← Back to all news

Retrieval-augmented generation

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

6,383 stories · RSS feed

arXiv Computer Vision
Aug 25

EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignment

EXPL-FR is a lightweight adapter that aligns a vision‑language model’s image encoder with a frozen face‑recognition (FR) embedding space, enabling the FR model to be explained using semantic attribute prompts without any text training. By mapping 978 attribute prompts across 22 categories into the FR space, the method identifies the most detectable concepts—forming a readable semantic signature that better separates identities than the full vocabulary. The approach is evaluated on four FR backbones and two VLM encoders, providing identity‑level, per‑image, and differential explanations, and demonstrates that prompt‑driven audits can rank FR models by per‑ethnicity error and attribute‑change verification cost without requiring labeled data.

By Guray Ozgur, Mustafa Efe Tamyapar, Naser Damer, Fadi Boutros
llmsragmultimodalbenchmarkssafety
More like this →
arXiv AI
Aug 25

LLM-Specific Utility for Retrieval-Augmented Generation

The paper introduces the concept of LLM‑specific utility, defining it as the performance gain a target large language model (LLM) achieves when provided with a passage compared to answering without evidence. A benchmark of utilitarian passages is built for four LLMs (Qwen3‑8B/14B/32B and Llama 3.1‑8B) across three QA datasets, revealing that each model benefits most from its own tailored evidence and that evidence optimized for other models is consistently suboptimal. The authors also create SpecUBench, a benchmark for LLM‑specific utility judgment, and show that current utility‑aware retrieval methods largely capture model‑agnostic usefulness, struggling to estimate LLM‑specific utility. "whyItMatters":"The study demonstrates that retrieval‑augmented generation must consider model‑specific evidence selection to truly improve LLM performance, highlighting a gap in existing utility‑aware methods."

By Hengran Zhang, Keping Bi, Jiafeng Guo, Jiaming Zhang, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng
llmsragbenchmarks
More like this →
arXiv Statistics ML
Aug 25

Sparse Separable Factor Analysis in the Complex Domain with an Application to Local Field Potential Data

The paper introduces Sparse Separable Factor Analysis (SSFA), a latent factor model designed for complex-valued arrays that preserves amplitude and phase information. SSFA models each mode’s covariance with a low‑rank Hermitian factor structure plus a diagonal residual, applying element‑wise lasso penalties to achieve interpretable, phase‑preserving loadings via complex soft‑thresholding. The method is validated through simulations showing improved covariance estimation over vectorization approaches and applied to local field potential data from mice to compare separability across brain region, frequency, and time, as well as to impute missing recordings due to electrode misplacement.

By Ian Hultman, Kirtikanth Kalapatapu, Yassine Filali, Rainbo Hultman, Sanvesh Srivastava
rag
More like this →
arXiv AI
Aug 25

Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules

Mol-JEPA is a scalable multimodal framework that learns molecular world models by using modality masking instead of suboptimal perturbations. It incorporates diverse data such as molecular structures, cellular phenotypes, binding affinities, ADMET profiles, quantum chemistry simulations, and other drug‑discovery information. Benchmarks show that the representations it learns perform strongly, highlighting the benefit of embedding biochemical context via latent‑space prediction.

By Florian Rottach, Sebastian Schieferdecker, William Rudman, Randall Balestriero, Carsten Eickhoff
ragdiffusionmultimodalbenchmarks
More like this →
arXiv AI
Aug 25

AI University: An LLM-Powered Learning Assistant for Engineering---A Finite Element Method Case Study

AI University (AI‑U) is a flexible framework that uses a fine‑tuned large language model (LLM) combined with retrieval‑augmented generation (RAG) and a reasoning synthesis model to produce style‑aligned responses from lecture videos, notes, and textbooks. In a graduate‑level finite‑element‑method (FEM) course, the authors created a pipeline to generate course‑grounded training data, fine‑tuned an open‑source LLM with Low‑Rank Adaptation (LoRA), and applied RAG‑based synthesis. Evaluation through cosine similarity, LLM‑based assessment, expert review, and user studies showed that the expert model outperformed the base model in alignment with course materials, with 86 % of test cases scoring higher and human users preferring the expert model roughly twice as often. whyItMatters":"The study demonstrates a practical method for building course‑specific learning assistants that improve alignment with instructional content, offering a template that can be extended across STEM fields."

By Mostafa Faghih Shojaei, Rahul Gulati, Benjamin A. Jasperson, Shangshang Wang, Simone Cimolato, Manas Vardhan, Dangli Cao, Willie Neiswanger, Krishna Garikipati
llmsragfine-tuningsafety
More like this →
arXiv AI
Aug 25

Hyperbolic Hierarchical Clustering for Visual Representation Learning

The paper introduces ClusterMixer, a token mixer based on hierarchical clustering in hyperbolic space, designed to be transparent and interpretable. It forms the core of a new vision backbone called HCFormer, which incorporates multiple clustering strategies to maintain strong performance. Experiments show HCFormer surpasses existing backbones on tasks such as image classification, object detection, instance segmentation, and semantic segmentation.

By Jianan Wei, Guikun Chen, Zhiyuan Weng, Chunchao Guo, Yujia Wang, Wenguan Wang
llmsragcomputer-visionsafety
More like this →