concept

retrieval

Facts (18)

Sources

Self-awareness, self-regulation, and self-transcendence (S-ART) frontiersin.org Frontiers in Human Neuroscience 2 facts

referenceQuirk and Mueller (2008) reviewed the neural mechanisms involved in extinction learning and retrieval.

referenceThe Self-awareness, self-regulation, and self-transcendence (S-ART) framework posits that mindfulness involves working memory, efficiency of memory encoding, retrieval, and extinction processes, all of which are aspects of hippocampal and parahippocampal activity.

Construction of intelligent decision support systems through ... - Nature nature.com Nature Oct 10, 2025 2 facts

referenceThe RAG-Only baseline system used in the IKEDS framework evaluation utilizes identical retrieval and generation components to the IKEDS framework but treats all knowledge as unstructured text without structured knowledge representation.

claimInnovations in the IKEDS framework include multi-layered knowledge graphs with cross-domain mappings, optimized retrieval, dynamic orchestration, context-aware generation, and multi-level explanations.

A Survey of Incorporating Psychological Theories in LLMs - arXiv arxiv.org arXiv 2 facts

claimZhu et al. (2024) employ recitation methods for retrieval, while Park & Bak (2024) introduce separate short- and long-term memory modules to LLM architectures.

claimSelf-reflection and meta-cognition, as defined by Phillips (2020) and Flavell (1979), support iterative introspection to improve retrieval (Asai et al., 2024) and multi-step inference (Zhou et al., 2024) in LLMs.

RAG Hallucinations: Retrieval Success ≠ Generation Accuracy linkedin.com Sumit Umbardand · LinkedIn Feb 6, 2026 2 facts

procedureRecommended RAG evaluation strategies include prioritizing retrieval, utilizing hybrid evaluation methods, and implementing continuous monitoring per release rather than relying on one-time testing.

claimIn RAG systems, most production issues originate from poor retrieval rather than generation, meaning that if the correct context is not fetched, the model cannot produce reliable answers.

A survey on augmenting knowledge graphs (KGs) with large ... link.springer.com Springer Nov 4, 2024 2 facts

claimThe synchronization of retrieval and generation components in RAG-based systems increases maintenance complexity, which may hinder their widespread adoption.

claimThe computational expense of Retrieval-augmented generation (RAG) is significant because it is a two-step process requiring vast computational resources for both retrieval and generation.

Bridging the Gap Between LLMs and Evolving Medical Knowledge arxiv.org arXiv Jun 29, 2025 1 fact

referenceHarsh Trivedi et al. (2022) published 'Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions' as an arXiv preprint (arXiv:2212.10509), which discusses combining retrieval with reasoning.

Efficient Knowledge Graph Construction and Retrieval from ... - arXiv arxiv.org arXiv Aug 7, 2025 1 fact

claimGraph Neural Networks (GNNs) encode graph structure and generate node embeddings for retrieval, but their inference speed is a bottleneck in large-scale systems because the computational cost of message passing across millions of nodes and edges hinders real-time applicability in low-latency enterprise settings (Chiang et al., 2019).

Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org Frontiers 1 fact

claimThe GoG framework (Xu et al., 2024) utilizes a generate-retrieve architecture to mitigate retrieval issues, but it suffers from semantic deviations during the generation phase that cause retrieval results to deviate from user intent.

vectara/hallucination-leaderboard - GitHub github.com Vectara 1 fact

referenceOpen-RAG-Eval is an open-source RAG (Retrieval-Augmented Generation) evaluation framework that utilizes the HHEM model and provides metrics for retrieval, groundedness, and citations.

Awesome-Hallucination-Detection-and-Mitigation - GitHub github.com GitHub 1 fact

referenceThe paper "Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity" by Wang et al. (2023) provides a survey on the state of factuality in large language models, covering aspects of knowledge, retrieval, and domain-specificity.

KG-IRAG: A Knowledge Graph-Based Iterative Retrieval-Augmented ... arxiv.org arXiv Mar 18, 2025 1 fact

referenceThe KG-IRAG evaluation uses three question types: Q1, which is a fundamental entity recognition and retrieval task; and Q2 and Q3, which introduce logical reasoning by incorporating time-dependent queries to test iterative reasoning over time.

Empowering GraphRAG with Knowledge Filtering and Integration arxiv.org arXiv Mar 18, 2025 1 fact

claimLLMs tend to over-rely on external information, which can degrade generation quality when retrieval is insufficient or the quality of retrieved knowledge is low.

Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv Sep 22, 2025 1 fact

referenceRoy et al. (2024) published 'Learning when to retrieve, what to rewrite, and how to respond in conversational QA' in EMNLP, pages 10604–10625, focusing on decision-making processes in conversational question answering.