Fine-grained Analysis of Brain-LLM Alignment through Input Attribution

arXiv:2510.12355 · cs.CL · Submitted 2025-10-14 · Read on arXiv

cs.CL

Submitted: 2025-10-14

Updated: 2026-10-13

Code: https://github.com/michelaproietti/Brain-LLM-Alignment-Attribution

Terminology

• Alignment — 5× in this paper · explained in 1 episode
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• From Language to Cognition: How LLMs Outgrow the Human Language Network
• The Zamba2 Suite: Technical Report
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Efficiently Modeling Long Sequences with Structured State Spaces
• Captum: A unified and generic model interpretability library for PyTorch
• Gemma: Open Models Based on Gemini Research and Technology
• Emergence of the Primacy Effect in Structured State-Space Models
• Explanations of Large Language Models Explain Language Representations in the Brain
• Exploiting Primacy Effect To Improve Large Language Models
• Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
• HuggingFace's Transformers: State-of-the-art Natural Language Processing

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering