concept

symbolic representation

Also known as: symbolic representation, symbolic representations

Facts (19)

Sources

A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Springer Dec 9, 2025 6 facts

procedureIn a hybrid neuro-symbolic architecture, the neural component processes raw data, transforms it into a symbolic representation, and employs a symbolic inference engine to reach a logically consistent conclusion.

claimA primary driver for the integration of neural and symbolic AI is the quest for explainability, as neural networks are often criticized as 'black boxes' with internal decision processes that are difficult to interpret and debug, whereas symbolic representations allow for explicit explanations and traceable decision paths.

claimNeuro-symbolic AI enables novel capabilities including extracting structured knowledge from raw data, dynamically generating new symbolic representations for novel concepts learned by neural networks, and using knowledge-based reasoning to refine and guide neural inference.

referenceUnified approaches in neuro-symbolic AI aim to embed both neural and symbolic representations within a shared framework, where symbols are encoded as continuous vectors to enable symbolic manipulation within the differentiable space of neural models.

claimReasoning over stable symbolic representations can significantly enhance an AI system’s robustness to minor input perturbations, such as noise or adversarial distortions.

claimSymbolic representations in neuro-symbolic systems allow for generalization based on combinatorial rules by capturing the underlying structure and concepts of a domain.

Neuro-Symbolic AI: Explainability, Challenges, and Future Trends arxiv.org arXiv Nov 7, 2024 3 facts

referenceXinyun Chen, Chen Liang, Adams Wei Yu, Denny Zhou, Dawn Song, and Quoc V Le developed the Neural Symbolic Reader, which integrates distributed and symbolic representations for reading comprehension, as presented at the International Conference on Learning Representations in 2019.

referenceGrzegorz Chrupała and Afra Alishahi investigated the correlation between neural and symbolic representations of language in a 2019 arXiv preprint.

referenceEmanuele Sansone and Robin Manhaeve proposed a method for learning symbolic representations through joint generative and discriminative training in their 2023 arXiv preprint.

Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org arXiv Feb 16, 2025 2 facts

procedureThe detect-understand-act (DUA) framework operates in three stages: the detect module uses computer vision to process unstructured data into symbolic representations; the understand component uses answer set programming (ASP) and inductive logic programming (ILP) to ensure decisions align with symbolic rules; and the act component uses pre-trained reinforcement learning policies to refine symbolic representations.

referenceHanlin Zhang, YiFan Zhang, Li Erran Li, and Eric Xing authored 'The impact of symbolic representations on in-context learning for few-shot reasoning', which was presented at the NeurIPS 2022 Workshop on Neuro Causal and Symbolic AI (nCSI).

Symbols and grounding in large language models - PMC pmc.ncbi.nlm.nih.gov E Pavlick · PMC 1 fact

claimEllie Pavlick argues that large language models can serve as plausible models of human language, providing counterarguments to two commonly cited reasons why they cannot: their lack of symbolic representations and their lack of grounding.

[PDF] Do LLMs Build World Representations? Probing Through the Lens ... proceedings.neurips.cc NeurIPS 1 fact

claimMental models are defined as systems capable of building abstract and symbolic representations of entities and their relations within the real world or the surrounding environment.

(PDF) Language and Consciousness; How Language Implies Self ... academia.edu Academia.edu 1 fact

claimSelf-referential cognition depends on symbolic representation rather than pre-linguistic awareness, according to the 2017 paper in 'Studies in Logic, Grammar and Rhetoric'.

The Synergy of Symbolic and Connectionist AI in LLM-Empowered ... arxiv.org arXiv Jul 11, 2024 1 fact

claimConnectionist artificial intelligence focuses on neural networks, whereas symbolic artificial intelligence emphasizes symbolic representation and logic.

Symbols and grounding in large language models royalsocietypublishing.org Royal Society Publishing Jun 5, 2023 1 fact

claimMultiple studies conducted in recent years suggest that symbolic representations play a causal role in probabilistic large language models.

Evolutionary Psychology | Internet Encyclopedia of Philosophy iep.utm.edu Internet Encyclopedia of Philosophy 1 fact

referenceThe 'Computational Theory of Mind', developed by philosophers such as Hilary Putnam and Jerry Fodor, conceives of mental states as relations between a thinker and symbolic representations, and mental processes as formal operations on the syntactic features of those representations.

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

The Mechanisms of Psychedelic Visionary Experiences - Frontiers frontiersin.org Frontiers Sep 27, 2017 1 fact

claimThe mirror neuron system was central in the evolution of human cognitive and symbolic capacities of imitation, mimesis, and symbolic representation.