# LLMs as a synthesis between symbolic and distributed approaches to language

arXiv: https://arxiv.org/abs/2502.11856 · HTML: https://mlsanity.com/paper/2502.11856/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 102 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets](https://mlsanity.com/paper/2201.02177/) (2022)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [Finding Neurons in a Haystack: Case Studies with Sparse Probing](https://mlsanity.com/paper/2305.01610/) (2023)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State](https://mlsanity.com/paper/1903.03260/) (2019)
- [Identifying and Controlling Important Neurons in Neural Machine Translation](https://mlsanity.com/paper/1811.01157/) (2018)
- [Circuit Component Reuse Across Tasks in Transformer Language Models](https://mlsanity.com/paper/2310.08744/) (2023)
- [Universal Neurons in GPT2 Language Models](https://mlsanity.com/paper/2401.12181/) (2024)
- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [Information Flow Routes: Automatically Interpreting Language Models at Scale](https://mlsanity.com/paper/2403.00824/) (2024)
- [Do Attention Heads in BERT Track Syntactic Dependencies?](https://mlsanity.com/paper/1911.12246/) (2019)
- [Distributional Semantics and Linguistic Theory](https://mlsanity.com/paper/1905.01896/) (2019)
- [How Linguistics Learned to Stop Worrying and Love the Language Models](https://mlsanity.com/paper/2501.17047/) (2025)
- [Explaining How Transformers Use Context to Build Predictions](https://mlsanity.com/paper/2305.12535/) (2023)
- [Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses](https://mlsanity.com/paper/2104.14694/) (2021)
- [SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding](https://mlsanity.com/paper/2204.10050/) (2022)
- [On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task](https://mlsanity.com/paper/2410.06496/) (2024)
- [Discovering Salient Neurons in Deep NLP Models](https://mlsanity.com/paper/2206.13288/) (2022)
- [Word Usage Similarity Estimation with Sentence Representations and Automatic Substitutes](https://mlsanity.com/paper/1905.08377/) (2019)
- [CoAM: Corpus of All-Type Multiword Expressions](https://mlsanity.com/paper/2412.18151/) (2024)
- [Why transformers are obviously good models of language](https://mlsanity.com/paper/2408.03855/) (2024)

## Built on by (most cited first, 13 of 13)

- [Language models as tools for investigating the distinction between possible and impossible natural languages](https://mlsanity.com/paper/2512.09394/) (2025)
- [Large language models have learned to use language](https://mlsanity.com/paper/2512.12447/) (2025)
- [Large language models are not about natural language](https://mlsanity.com/paper/2512.13441/) (2025)
- [Linguists should learn to love speech-based deep learning models](https://mlsanity.com/paper/2512.14506/) (2025)
- [Are Language Models Models?](https://mlsanity.com/paper/2601.10421/) (2026)
- [Sparse or Dense? A Mechanistic Estimation of Computation Density in Transformer-based LLMs](https://mlsanity.com/paper/2601.22795/) (2026)
- [Blackbird Language Matrices: A Framework to Investigate the Linguistic Competence of Language Models](https://mlsanity.com/paper/2602.20966/) (2026)
- [Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated Probabilities](https://mlsanity.com/paper/2604.09466/) (2026)
- [You Can't Fight in Here! This is BBS!](https://mlsanity.com/paper/2604.09501/) (2026)
- [Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear](https://mlsanity.com/paper/2605.10061/) (2026)
- [Tracing Computation Density in LLMs](https://mlsanity.com/paper/2605.27033/) (2026)
- [Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation](https://mlsanity.com/paper/2608.22034/) (2026)
- [A Formal Limitation on Learning Human Language From Textual Corpora](https://mlsanity.com/paper/2608.28560/) (2026)

## Abstract (arXiv)

Since the middle of the 20th century, a fierce battle is being fought between symbolic and distributed approaches to language and cognition. The success of deep learning models, and LLMs in particular, has been alternatively taken as showing that the distributed camp has won, or dismissed as an irrelevant engineering development. In this position paper, I argue that deep learning models for language actually represent a synthesis between the two traditions. This is because 1) deep learning architectures allow for both distributed/continuous/fuzzy and symbolic/discrete/categorical-like representations and processing; 2) models trained on language make use of this flexibility. In particular, I review recent research in interpretability that showcases how a substantial part of morphosyntactic knowledge is encoded in a near-discrete fashion in LLMs. This line of research suggests that different behaviors arise in an emergent fashion, and models flexibly alternate between the two modes (and everything in between) as needed. This is possibly one of the main reasons for their wild success; and it makes them particularly interesting for the study of language. Is it time for peace?