Retrieval-augmented generation

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

2,965 stories · RSS feed

arXiv AI

Aug 10

Flowing Through States: Neural ODE Regularization for Reinforcement Learning

arXiv:2608. 06595v1 Announce Type: cross Abstract: Neural networks applied to sequential decision-making tasks typically rely on latent representations of environment states.

By Mohamed Ghanem, Bernd Finkbeiner

rag agents reinforcement-learning benchmarks

arXiv AI

Aug 10

KReF: Training-Free Retrieval for Long-Term Time-Series Forecasting and Predictive Uncertainty

arXiv:2608. 06748v1 Announce Type: cross Abstract: Probabilistic long-term time-series forecasting commonly relies on trained models.

By Yang Zhang, Rui Su

rag benchmarks safety

arXiv AI

Aug 10

PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue

arXiv:2608. 06975v1 Announce Type: cross Abstract: Long-horizon role-playing demands that characters remain recognizable as they evolve with the narrative.

By Bo Tang, Jianan Yang, Junyi Zhu, Yiquan Wu, Rui Zhao, Zhengyu Yang, Yang Zhang, Feiyu Xiong, Zhiyu Li, Jiajun Shen

llms rag benchmarks

arXiv AI

Aug 10

Towards a Theoretical Understanding of Two Tower Recommendation Models

arXiv:2403. 00802v2 Announce Type: replace-cross Abstract: Production-grade recommender systems rely heavily on a large-scale corpus used by online media services, including Netflix, Pinterest, and Amazon.

By Amit Kumar Jaiswal

rag

arXiv AI

Aug 10

QFCQT: A Chaotically Gated Quantformer Framework for Volatile Time-Series Forecasting

arXiv:2608. 07363v1 Announce Type: new Abstract: Forecasting non-stationary time series remains difficult due to long-range dependencies, local volatility bursts, structural shifts, and nonlinear oscillatory behaviors.

By Junkai Lin, Siqi Hou, Raymond Lee

llms rag benchmarks

arXiv Machine Learning

Aug 10

Understanding Differentiable Embeddings Through Differential and Integral Geometry

arXiv:2608. 06809v1 Announce Type: new Abstract: How can an analyst decide whether a nonlinear dimensionality reduction embedding can be trusted?

By Xinyu Zhang, Klaus Mueller

rag

arXiv AI

Aug 10

bioMoR: Biology-Guided Mixture-of-Recursions for Effective Genomic Learning

arXiv:2608. 06727v1 Announce Type: new Abstract: Transformer models for high-dimensional omics analysis process thousands of genes or pathways, although only a subset requires deep computation.

By Koushik Howlader, Tirtho Roy, Md Tauhidul Islam, Wei Le

llms rag benchmarks safety

arXiv AI

Aug 10

Representation-driven Endoscopic Visual Embedding Alignment for Latent Generation

arXiv:2608. 07176v1 Announce Type: cross Abstract: Developing foundation generative models for endoscopy is limited by the gap between natural and clinical images and the computational cost of training large Diffusion Transformers.

By Francisco Caetano, Tim J. M. Jaspers, Haiko Middeljans, Martijn R. Jong, Rixta A. H. van Eijck van Heslinga, Floor Slooter, Albert J. de Groof, Jacques J. Bergman, Peter H. N. De With, Fons van der Sommen

llms rag diffusion computer-vision benchmarks safety

arXiv Machine Learning

Aug 10

Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction

arXiv:2608. 07420v1 Announce Type: new Abstract: World models are expected to support imagination over extended temporal horizons, yet most are still trained through local few-step prediction objectives and deployed by recursively rolling out their own predictions.

By Xinyi Li, Zaishuo Xia, Chenjie Hao, Yubei Chen

rag benchmarks

arXiv AI

Aug 10

Harnessing the Synergy between LLM Agents and Knowledge Graphs for Urban Socioeconomic Prediction

arXiv:2411. 00028v3 Announce Type: replace-cross Abstract: Socioeconomic prediction aims to leverage various urban data to predict the socioeconomic indicators of regions such as population and commercial activity level, which plays an important role in understanding urban regions and supporting decision-making.

By Zhilun Zhou, Jingyang Fan, Yu Liu, Fengli Xu, Depeng Jin, Yong Li

llms rag agents

arXiv Machine Learning

Aug 10

Embedded Variational Neural Stochastic Differential Equations for Learning Heterogeneous Dynamics

arXiv:2604. 00669v2 Announce Type: replace Abstract: This study examines the challenges of modeling complex and noisy data related to socioeconomic factors over time, with a focus on data from various districts in Odisha, India.

By Sandeep Kumar Samota, Reema Gupta, Snehashish Chakraverty

rag diffusion

arXiv AI

Aug 10

FinRank: An Evidence-Grounded Benchmark for Financial Question Answering and Retrieval over SEC Filings

arXiv:2608. 07400v1 Announce Type: new Abstract: Financial question answering is typically evaluated by answer correctness, yet in SEC filings a plausible and even numerically correct answer can be grounded in the wrong evidence.

By Sasan Mansouri, Daniel Saad, Mark Wahrenburg, Manu Weissel, Fabian Woebbeking

rag nlp benchmarks

arXiv Machine Learning

Aug 10

Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMs

arXiv:2509. 16462v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used in high-stakes decision-making systems, where biased predictions can reinforce social and economic disparities.

By Mina Arzaghi, Alireza Dehghanpour Farashah, Florian Carichon, Jean-Fran\c{c}ois Plante, Golnoosh Farnadi

llms rag fine-tuning benchmarks safety

arXiv AI

Aug 10

Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers

arXiv:2608. 07436v1 Announce Type: new Abstract: Under the standard split, Muon gets hidden matrices and AdamW embeddings/output head.

By Ali Janati, Kaoutar El Maghraoui, Andrei Kanavalau, Anass Belfatmi

llms rag safety

arXiv Machine Learning

Aug 10

SNI-GNN: SmartNIC-Assisted Full-Graph GNN Training with In-Network Embedding Prediction

arXiv:2608. 06441v1 Announce Type: new Abstract: Full-graph GNN training delivers high accuracy but scales poorly on multi-server clusters due to heavy, irregular inter-node embedding exchanges.

By Guofan Yu, Sitian Chen, Zhenheng Tang, Xiaowen Chu, Amelie Chi Zhou

rag benchmarks safety data-engineering

arXiv AI

Aug 10

Soft Redaction of Image Provenance via Zero-Knowledge Proofs

arXiv:2608. 07063v1 Announce Type: cross Abstract: Content provenance standards, such as C2PA, are increasingly used to attach signed records of origin, editing history, and rights to digital images.

By Muhammad Awan, John Collomosse

rag safety

arXiv AI

Aug 10

SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimization

arXiv:2602. 12187v2 Announce Type: replace-cross Abstract: Search-Augmented Generative Engines (SAGE) have emerged as a new paradigm for information access, bridging web-scale retrieval with generative capabilities to deliver synthesized answers.

By Sunghwan Kim, Wooseok Jeong, Serin Kim, Sangam Lee, Dongha Lee

rag benchmarks

arXiv AI

Aug 10

SCALE: Scientific Concept Aggregation via LLMs and Embeddings for Fine-Grained Taxonomy Extension

arXiv:2608. 07254v1 Announce Type: cross Abstract: The increasing specialization of scientific research challenges existing classification systems, which provide effective representations of broad disciplines and research topics but often fail to capture the fine-grained conceptual structure of contemporary science.

By Daniele Raimondi, Feichi Lu, Oliver Grun, Mariia Eremina, Andrea Perlato

llms rag

arXiv Machine Learning

Aug 10

Addressable Memory for Video World Models

arXiv:2608. 07408v1 Announce Type: cross Abstract: We study visual persistence in interactive video world models.

By Xindi Wu, Sven Elflein, James Lucas, Olga Russakovsky, Laura Leal-Taix\'e, Despoina Paschalidou, Jonathan Lorraine, Aljo\v{s}a O\v{s}ep

rag benchmarks

arXiv AI

Aug 10

WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model Watermarking

arXiv:2608. 06416v1 Announce Type: cross Abstract: Watermarking traces the provenance of text produced by large language models by embedding statistically detectable signals during decoding.

By Song Xiao, Yuqi Yuan, Yanshuo Zhang, Kejun Zhang

llms rag