Knowledge Tree
generative models
Also known as: generative model, generative modeling, large generative models
Facts (23)
Sources
Construction of intelligent decision support systems through ... - Nature nature.com Oct 10, 2025 3 facts
claimThe proposed architecture combines generative models enhanced by external knowledge retrieval with structured, linked representations of domain knowledge to improve decision accuracy, reasoning transparency, and context relevance.
claimRetrieval-augmented generation improves the factual grounding of generated content while maintaining the flexibility and natural language capabilities of generative models.
claimThe proposed framework includes a flexible knowledge orchestration layer designed to optimize information exchange between structured knowledge graph representations and generative model capabilities.
Track: Poster Session 3 - aistats 2026 virtual.aistats.org 3 facts
claimThe Geometry-Aware Generative Autoencoder (GAGA) framework combines extensible manifold learning with generative modeling to address computational and statistical challenges in geometry-aware data generation, trajectory interpolation, and population transport.
claimZilong Deng, Simon Khan, and Shaofeng Zou study the sample complexity of risk-sensitive Reinforcement Learning with a generative model, specifically focusing on maximizing the Conditional Value at Risk (CVaR) with a risk tolerance level tau at each step, a problem they name Iterated CVaR.
claimStochastic simulation models are generative models that mimic complex systems to assist with decision-making.
Combining large language models with enterprise knowledge graphs frontiersin.org Aug 26, 2024 2 facts
claimGenerative models like ChatGPT can quickly become outdated or change unexpectedly, which compromises the reproducibility and efficiency of prompting techniques, according to Törnberg (2024).
claimThe opacity of training data in generative models like ChatGPT makes them less reliable in zero-shot scenarios.
Large Language Models Meet Knowledge Graphs for Question ... arxiv.org Sep 22, 2025 2 facts
referenceRAMQA enhances multi-modal retrieval-augmented question-answering by integrating learning-to-rank with the training of generative models via multi-task learning.
referenceFeng et al. (2025) demonstrated that retrieval in decoder benefits generative models for explainable complex question answering, published in the journal Neural Networks (181:106833).
A Survey on the Theory and Mechanism of Large Language Models arxiv.org Mar 12, 2026 2 facts
claimGan and Liu (2025) propose a 'reverse-bottleneck' framework, which posits that a post-trained model’s generalization error upper bound is negatively correlated with the 'information gain' obtained from the generative model.
referenceThe paper 'No free lunch: fundamental limits of learning non-hallucinating generative models' is an arXiv preprint (arXiv:2410.19217).
Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org 2 facts
referenceKGValidator, proposed by Boylan et al. in 2024, is a consistency and validation framework for knowledge graphs that uses generative models and supports any external knowledge source.
referenceKGPT, proposed by Chen et al. in 2020, comprises a generative model for producing knowledge-enriched text and a pre-training paradigm on a large corpus of knowledge text crawled from the web.
Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org Feb 16, 2025 1 fact
claimRecent studies have demonstrated that neuro-symbolic AI approaches are effective in applications such as design generation and enhancing the instructability of generative models.
Understanding LLM Understanding skywritingspress.ca Jun 14, 2024 1 fact
claimGenerative models, including Large Language Models, are key for self-supervised learning, marking a generative turn in artificial intelligence.
Neuro-Symbolic AI: Explainability, Challenges & Future Trends linkedin.com Dec 15, 2025 1 fact
perspectiveA shift towards using generative models could enhance the reliability and adaptability of AI systems for data scientists and AI developers.
RAG Using Knowledge Graph: Mastering Advanced Techniques procogia.com Jan 15, 2025 1 fact
claimRetrieval-Augmented Generation (RAG) is a paradigm that combines retrieval-based and generative models to generate contextually rich responses by leveraging external information repositories.
Not Minds, but Signs: Reframing LLMs through Semiotics - arXiv arxiv.org Jul 1, 2025 1 fact
referenceGanguli et al.'s 2022 paper 'Predictability and surprise in large generative models' analyzes the behavior of large generative models.
AI Sessions #9: The Case Against AI Consciousness (with Anil Seth) conspicuouscognition.com Feb 17, 2026 1 fact
claimPredictive regulation allows an organism to maintain physiological variables by using a generative model to set priors as 'set points'.
A survey on augmenting knowledge graphs (KGs) with large ... link.springer.com Nov 4, 2024 1 fact
referenceIzacard and Grave authored 'Leveraging passage retrieval with generative models for open domain question answering', an arXiv preprint published in 2020 (arXiv:2007.01282).
A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Dec 9, 2025 1 fact
claimFormal logic can be utilized to encode safety or ethical constraints within generative models.
vectara/hallucination-leaderboard - GitHub github.com 1 fact
claimThe creators of the Vectara hallucination leaderboard assert that building a model for detecting hallucinations is significantly easier than building a generative model that never produces hallucinations.