concept

inference

Also known as: inferences, inferencing

Facts (23)

Sources

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

claimDynaThink is a technique that dynamically selects between rapid or thorough inference for Large Language Models.

referenceSchema Theory holds that humans store knowledge as dynamic, structured representations formed through repeated experience, which guide inference, memory, and learning.

EdinburghNLP/awesome-hallucination-detection - GitHub github.com GitHub 2 facts

claimThe EdinburghNLP awesome-hallucination-detection repository provides a taxonomy of error types for AI systems, including comprehension, factualness, specificity, and inference.

referenceEvaluation metrics for AI systems include counts of correct and wrong answers, as well as failure counts categorized by comprehension, factualness, specificity, and inference.

A Survey on the Theory and Mechanism of Large Language Models arxiv.org arXiv Mar 12, 2026 2 facts

claimThe survey titled 'A Survey on the Theory and Mechanism of Large Language Models' organizes the theoretical landscape of Large Language Models into a lifecycle-based taxonomy consisting of six stages: Data Preparation, Model Preparation, Training, Alignment, Inference, and Evaluation.

claimA central theoretical paradox in large language model research is how models with frozen parameters can effectively learn new tasks or provide different response qualities based on query phrasing during inference.

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

referenceATOMIC is a large-scale knowledge graph of everyday commonsense knowledge used as a benchmark to evaluate models on inference and explanation generation.

claimKG-enhanced LLMs are categorized into three research areas: pre-training, inference, and interpretability.

Hallucination Causes: Why Language Models Fabricate Facts mbrenndoerfer.com M. Brenndoerfer · mbrenndoerfer.com Mar 15, 2026 1 fact

formulaInference in large language models computes the probability of the next token, denoted as P(y_hat_t | y_hat_<t), where y_hat_t is the token the model generates at step t and y_hat_<t represents the model's own previously generated tokens.

Applying Large Language Models in Knowledge Graph-based ... arxiv.org Benedikt Reitemeyer, Hans-Georg Fill · arXiv Jan 7, 2025 1 fact

claimOntologies use formal notation and axioms to enable reasoning and inferencing, which allows for the derivation of new knowledge.

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

claimPrompt-based methods for knowledge graph completion, such as ProLINK and TAGREAL, cannot fully resolve the fundamental ambiguity between factual recall and genuine inference, which is a significant limitation in healthcare applications where provenance is critical.

Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org arXiv Feb 16, 2025 1 fact

claimReasoning and inference methods, such as chain-of-thought (CoT) reasoning and link prediction, enhance the logical decision-making capabilities of AI systems.

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

referenceThe LPKG method, proposed by Wang et al. in 2024, involves Planning LLM Tuning, Inference, and Execution using GPT-3.5-Turbo, CodeQwen1.5-7B-Chat, and Llama-3-8B-Instruct models with dataset-inherent knowledge graphs (Wikidata) and Wikidata15K for KGQA and Multi-hop QA, evaluated using EM, P, and R metrics on the HotpotQA, 2WikiMQA, Bamboogle, MuSiQue, and CLQA-Wiki datasets.

KG-IRAG with Iterative Knowledge Retrieval - arXiv arxiv.org arXiv Mar 18, 2025 1 fact

claimMost Retrieval-Augmented Generation (RAG) methods struggle with multi-step reasoning tasks that require both information extraction and inference.

Construction of intelligent decision support systems through ... - Nature nature.com Nature Oct 10, 2025 1 fact

claimKnowledge graphs are proficient in modeling complicated domains and supporting inference, providing a structured basis for knowledge-intensive applications.

LLM-empowered knowledge graph construction: A survey - arXiv arxiv.org arXiv Oct 23, 2025 1 fact

referenceThe Graphusion framework (Yang et al., 2024) uses a unified, prompt-based paradigm to perform fusion subtasks—including alignment, consolidation, and inference—within a single generative cycle.

Track: Poster Session 3 - aistats 2026 virtual.aistats.org Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche · AISTATS 1 fact

claimProbabilistic circuits (PCs) are a unifying representation for probabilistic models that support tractable inference.

Classification Schemes of Altered States of Consciousness - ORBi orbi.uliege.be ORBi 1 fact

referenceCorlett et al. explored the relationship between glutamatergic model psychoses, prediction error, learning, and inference in their 2011 paper 'Glutamatergic model psychoses: prediction error, learning, and inference'.

claimSymbolic reasoning in knowledge graphs is defined as the process of deriving logical conclusions and making inferences based on symbolic representations of entities.

A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Springer Dec 9, 2025 1 fact

claimThe learning-reasoning paradigm embodies a bidirectional interplay where neural and symbolic modules iteratively inform and refine each other, with neural components extracting structured hypotheses and symbolic modules performing inference and feeding back structured signals.

Adversarial testing of global neuronal workspace and ... - Nature nature.com Nature Apr 30, 2025 1 fact

referenceFleming (2020) proposed a framework for awareness as inference within a higher-order state space in the journal Neuroscience of Consciousness.

Reference Hallucination Score for Medical Artificial ... medinform.jmir.org JMIR Medical Informatics Jul 31, 2024 1 fact

referenceWei et al. (2025) proposed a roadmap for robust and trustworthy medical AI by integrating statistical design and inference, published in The Innovation Medicine.

Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org arXiv 1 fact

claimSemantic reasoning and inference allow for the validation of a knowledge graph's consistency based on a given ontology or individual structural constraints.