# The Roles of Symbols in Neural-based AI: They are Not What You Think!

arXiv: https://arxiv.org/abs/2304.13626 · HTML: https://mlsanity.com/paper/2304.13626/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 38 references that are in the map.
- First posted on arXiv 26 Apr 2023.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective](https://mlsanity.com/paper/2003.00330/) (2020)
- [Relating Simple Sentence Representations in Deep Neural Networks and the Brain](https://mlsanity.com/paper/1906.11861/) (2019)

## Built on by (most cited first, 4 of 4)

- [From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks](https://mlsanity.com/paper/2310.11884/) (2023)
- [Metacognitive AI: Framework and the Case for a Neurosymbolic Approach](https://mlsanity.com/paper/2406.12147/) (2024)
- [A fuzzy loss for ontology classification](https://mlsanity.com/paper/2405.02083/) (2024)
- [Quantitative Linear Logic for Neuro-Symbolic Learning and Verification](https://mlsanity.com/paper/2605.13845/) (2026)

## Abstract (arXiv)

We propose that symbols are first and foremost external communication tools used between intelligent agents that allow knowledge to be transferred in a more efficient and effective manner than having to experience the world directly. But, they are also used internally within an agent through a form of self-communication to help formulate, describe and justify subsymbolic patterns of neural activity that truly implement thinking. Symbols, and our languages that make use of them, not only allow us to explain our thinking to others and ourselves, but also provide beneficial constraints (inductive bias) on learning about the world. In this paper we present relevant insights from neuroscience and cognitive science, about how the human brain represents symbols and the concepts they refer to, and how today's artificial neural networks can do the same. We then present a novel neuro-symbolic hypothesis and a plausible architecture for intelligent agents that combines subsymbolic representations for symbols and concepts for learning and reasoning. Our hypothesis and associated architecture imply that symbols will remain critical to the future of intelligent systems NOT because they are the fundamental building blocks of thought, but because they are characterizations of subsymbolic processes that constitute thought.