# Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement

arXiv: https://arxiv.org/abs/2510.22860 · HTML: https://mlsanity.com/paper/2510.22860/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 12 of its 43 references that are in the map.
- First posted on arXiv 26 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 12 of 12)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought](https://mlsanity.com/paper/2210.01240/) (2022)
- [WinoGrande: An Adversarial Winograd Schema Challenge at Scale](https://mlsanity.com/paper/1907.10641/) (2019)
- [Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State](https://mlsanity.com/paper/1903.03260/) (2019)
- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [Self-supervised models of audio effectively explain human cortical responses to speech](https://mlsanity.com/paper/2205.14252/) (2022)
- [Joint processing of linguistic properties in brains and language models](https://mlsanity.com/paper/2212.08094/) (2022)
- [Training language models to summarize narratives improves brain alignment](https://mlsanity.com/paper/2212.10898/) (2022)
- [Speech Recognition and Multi-Speaker Diarization of Long Conversations](https://mlsanity.com/paper/2005.08072/) (2020)

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

- [From Chains to DAGs: Probing the Graph Structure of Reasoning in LLMs](https://mlsanity.com/paper/2601.17593/) (2026)
- [Training-Driven Representational Geometry Modularization Predicts Brain Alignment in Language Models](https://mlsanity.com/paper/2602.07539/) (2026)
- [Large Language Models Align with the Human Brain during Creative Thinking](https://mlsanity.com/paper/2604.03480/) (2026)
- [Grammatical "grandmother neurons" are rare in LLMs](https://mlsanity.com/paper/2609.29328/) (2026)

## Abstract (arXiv)

Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model neural responses to language, their internal representations are highly "entangled," mixing information about lexicon, syntax, meaning, and reasoning. This entanglement biases conventional brain encoding analyses toward linguistically shallow features (e.g., lexicon and syntax), making it difficult to isolate the neural substrates of cognitively deeper processes. Here, we introduce a residual disentanglement method that computationally isolates these components. By first probing an LM to identify feature-specific layers, our method iteratively regresses out lower-level representations to produce four nearly orthogonal embeddings for lexicon, syntax, meaning, and, critically, reasoning. We used these disentangled embeddings to model intracranial (ECoG) brain recordings from neurosurgical patients listening to natural speech. We show that: 1) This isolated reasoning embedding exhibits unique predictive power, accounting for variance in neural activity not explained by other linguistic features and even extending to the recruitment of visual regions beyond classical language areas. 2) The neural signature for reasoning is temporally distinct, peaking later (~350-400ms) than signals related to lexicon, syntax, and meaning, consistent with its position atop a processing hierarchy. 3) Standard, non-disentangled LLM embeddings can be misleading, as their predictive success is primarily attributable to linguistically shallow features, masking the more subtle contributions of deeper cognitive processing.