← 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 AI
Aug 25

LLM Evaluation on Unseen Questions: Contextual Multidimensional IRT Model

The paper proposes a model-based evaluation framework that merges multidimensional item response theory (IRT) with question context embeddings to predict large language model (LLM) performance on unseen questions. By representing LLMs with latent capability profiles and incorporating question content to inform item characteristics, the approach improves prediction accuracy over model-free baselines in within-scenario settings and offers a richer description of capability variation than unidimensional models. However, the study also finds that this generalizability does not reliably extend to cross-scenario shifts, indicating a key limitation for broader application.

By Ergan Shang, Weijing Tang, Yinqiu He
llmsrag
More like this →
arXiv Computation and Language
Aug 25

FCPRAG: Fusion-Controller Parametric Retrieval-Augmented Generation for Stable Multi-Passage LoRA Injection

FCPRAG introduces a fusion-controlled parametric retrieval‑augmented generation framework that uses a lightweight controller to predict per‑passage fusion scores and sample‑level calibration signals, such as a mixing gate and adaptive temperature. This approach mitigates the bottleneck of evidence‑level fusion when multiple passages are retrieved, enabling selective fusion under informative signals and conservative fusion under uncertainty. Experiments on HotpotQA, 2WikiMultiHopQA, PopQA, and ComplexWebQuestions demonstrate consistent F1 improvements over standard RAG and parametric RAG baselines, with gains up to 4.65% on 2WikiMultiHopQA and 7.55% on CWQ, while also reducing tuning cost and enhancing robustness to retrieval perturbations.

By Jinchang Zhu, Jindong Li, Yi Ding, Xiaojian Nie, Rong Fu, Shuangyong Song, Haowei He, Menglin Yang
llmsragfine-tuning
More like this →
arXiv Computer Vision
Aug 25

How Architecture and Training Affect TPC Representations Across Experiments

arXiv:2608.21756v1 Announce Type: cross Abstract: Deep-learning efforts have increasingly shifted toward foundation model approaches. In experimental physics, this allows models and learned represent...

By Tyler Wheeler, Michelle P. Kuchera, Raghuram Ramanujan, William Sieland, Ryan Krupp, Daniel Bazin, Connor L. Cross, Hoi Yan Ian Heung, Andrew J. Jones, Ruchi Mahajan, Saiprasad Ravishankar, Pranjal Singh, Benjamin Votaw, Chris Wrede
ragfine-tuning
More like this →
arXiv Computer Vision
Aug 25

Retrieval-Augmented Visual Prompting: Guiding Foundation Models in Two-Photon Imaging

arXiv:2608.21970v1 Announce Type: new Abstract: Two-photon calcium imaging presents a challenging setting for foundation models: image appearance varies substantially across recordings and experiment...

By Salvatore Calcagno, Marco Finocchiaro, Giovanni Bellitto, Daniela Giordano, Concetto Spampinato, Federica Proietto Salanitri
llmsragcomputer-visionfine-tuningbenchmarks
More like this →
arXiv AI
Aug 25

DeepRefine: Agentic Knowledge Refinement via Reinforcement Learning

DeepRefine is a reinforcement learning framework that improves the quality of pre‑constructed structured knowledge bases—such as knowledge graphs or LLM‑Wikis—by engaging in multi‑turn interactions with the base. It performs abductive diagnosis to locate defects, then applies targeted refinement actions to incrementally update the knowledge base. The system uses a Gain‑Beyond‑Draft reward to train its refinement policy end‑to‑end, achieving consistent downstream performance gains over strong baselines.

By Haoyu Huang, Jiaxin Bai, Shujie Liu, Yang Wei, Huihao Jing, Hong Ting Tsang, Yisen Gao, Zhongwei Xie, Yufei Li, Yangqiu Song
llmsragagentsreinforcement-learning
More like this →
arXiv AI
Aug 25

Semantic Substrate Dynamics Theory: An Operator-Theoretic Framework for Geometric Semantic Drift

Semantic Substrate Dynamics Theory (SSDT) proposes an operator‑theoretic framework that unifies various signals of semantic drift—such as embedding displacement, neighbor change, distributional divergence, and recursive trajectory instability—by treating them as observables of a time‑indexed substrate that couples embedding geometry to a local diffusion kernel. The theory distinguishes between within‑basin churn, basin crossing, recursion‑induced instability, and intervention‑order effects, using coarse Ricci curvature as a dense descriptor of basin and bridge geometry and bridge mass as a sparse node‑level indicator of genuine bridge structure. For recursive generation, SSDT decomposes node displacement into radial and tangential components, separating bounded departure from ongoing reinterpretation, and predicts future rewiring through a local density statistic rather than curvature aggregates.

By Stephen Russell
ragdiffusion
More like this →