# Generative causal testing to bridge data-driven models and scientific theories in language neuroscience

arXiv: https://arxiv.org/abs/2410.00812 · HTML: https://mlsanity.com/paper/2410.00812/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 65 references that are in the map.
- First posted on arXiv 1 Oct 2024.

## Builds on (most cited first, 15 of 15)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Neural General Circulation Models for Weather and Climate](https://mlsanity.com/paper/2311.07222/) (2023)
- [Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)](https://mlsanity.com/paper/1905.11833/) (2019)
- [Scaling laws for language encoding models in fMRI](https://mlsanity.com/paper/2305.11863/) (2023)
- [Veridical Data Science](https://mlsanity.com/paper/1901.08152/) (2019)
- [Explaining black box text modules in natural language with language models](https://mlsanity.com/paper/2305.09863/) (2023)
- [Describing Differences between Text Distributions with Natural Language](https://mlsanity.com/paper/2201.12323/) (2022)
- [Blackbox meets blackbox: Representational Similarity and Stability Analysis of Neural Language Models and Brains](https://mlsanity.com/paper/1906.01539/) (2019)
- [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)
- [BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity](https://mlsanity.com/paper/2310.04420/) (2023)

## Built on by (most cited first, 5 of 5)

- [Sanity Checks for Agentic Data Science](https://mlsanity.com/paper/2604.11003/) (2026)
- [Stroke Lesions as a Rosetta Stone for Language Model Interpretability](https://mlsanity.com/paper/2602.04074/) (2026)
- [Towards Interpretable Visual Decoding with Attention to Brain Representations](https://mlsanity.com/paper/2509.23566/) (2025)
- [Interpreting Brain Responses to Language with Sparse Features from Language Models](https://mlsanity.com/paper/2606.06857/) (2026)
- [What does it mean to understand language?](https://mlsanity.com/paper/2511.19757/) (2025)

## Abstract (arXiv)

Representations from large language models are highly effective at predicting BOLD fMRI responses to language stimuli. However, these representations are largely opaque: it is unclear what features of the language stimulus drive the response in each brain area. We present generative causal testing (GCT), a framework for generating concise explanations of language selectivity in the brain from predictive models and then testing those explanations in follow-up experiments using LLM-generated stimuli.This approach is successful at explaining selectivity both in individual voxels and cortical regions of interest (ROIs), including newly identified microROIs in prefrontal cortex. We show that explanatory accuracy is closely related to the predictive power and stability of the underlying predictive models. Finally, we show that GCT can dissect fine-grained differences between brain areas with similar functional selectivity. These results demonstrate that LLMs can be used to bridge the widening gap between data-driven models and formal scientific theories.