concept

reasoning processes

Also known as: reasoning mechanisms, reasoning process

Facts (10)

Sources

Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv Sep 22, 2025 2 facts

procedureIn offline KG guidelines, the Knowledge Graph supplies potential paths or subgraphs before the LLM begins the reasoning process, allowing the LLM to select the most relevant path for reasoning.

referenceLiang et al. (2025) proposed ReasVQA, a framework for advancing VideoQA by addressing imperfect reasoning processes (arXiv:2501.13536).

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

claimInterpretability research in KG-enhanced LLMs uses knowledge graphs to understand the knowledge learned by LLMs and to interpret their reasoning processes.

claimUsing an ensemble of different reasoning paths, improving the reasoning process, and fine-tuning Large Language Models with process-level feedback can help mitigate reasoning inconsistency.

Neuro-symbolic AI - Wikipedia en.wikipedia.org Wikipedia 1 fact

claimGary Marcus identifies four cognitive prerequisites for building robust artificial intelligence: (1) hybrid architectures that combine large-scale learning with the representational and computational powers of symbol manipulation, (2) large-scale knowledge bases—likely leveraging innate frameworks—that incorporate symbolic knowledge along with other forms of knowledge, (3) reasoning mechanisms capable of leveraging those knowledge bases in tractable ways, and (4) rich cognitive models that work together with those mechanisms and knowledge bases.

A Survey on the Theory and Mechanism of Large Language Models arxiv.org arXiv Mar 12, 2026 1 fact

referenceThe paper 'Rethinking external slow-thinking: from snowball errors to probability of correct reasoning' analyzes the impact of error propagation in external reasoning processes.

Neuro-Symbolic AI: Explainability, Challenges, and Future Trends arxiv.org arXiv Nov 7, 2024 1 fact

referenceYi et al. (2018) introduced a neural-symbolic visual question answering (VQA) system that disentangles reasoning processes from vision and language understanding.

Integrating Philosophy of Understanding With the Cognitive Sciences pmc.ncbi.nlm.nih.gov PMC 1 fact

claimA naturalized epistemology of understanding begins with the recognition that philosophers do not have a monopoly on studying reasoning processes.

A Survey of Incorporating Psychological Theories in LLMs - arXiv arxiv.org arXiv 1 fact

claimDual-process theory, a social cognition framework, distinguishes between fast (System 1) and slow (System 2) reasoning processes.

The Synergy of Symbolic and Connectionist AI in LLM ... arxiv.org arXiv 1 fact

claimChain-of-Thought (CoT) and Tree-of-Thoughts (ToT) reasoning mechanisms mitigate the limitations of token-level constraints in Large Language Models (LLMs).