arXiv AI
Uncovering the Computational Ingredients of Human-Like Representations in LLMs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 3
Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models
The paper extends mechanistic interpretability of large language models by modeling concepts as low‑dimensional non‑linear manifolds rather than linear subspaces. It introduces a concept‑based alignment (CBA) score to compare these manifolds across layers and models, revealing block structures in intermediate layers, a shift from syntax‑dominated to mixed syntactic‑semantic concepts, and training‑dependent multilingual sharing. The study also shows that alignment patterns differ across model families and training stages, with adjacent stages aligning more closely than distant ones.
arXiv Computation and Language
Sep 30
Cognitive Expert Language Models Better Align with the Corresponding Brain Systems
The study investigates whether language models tailored to specific cognitive domains better align with corresponding brain systems. By prompting and fine‑tuning large language models into six domain experts—sensory, spatial, numerical, reasoning, social, and abstract—the authors find that each expert’s representations more closely match the brain region associated with its domain than other experts. This domain‑specific alignment holds across multiple base models and fMRI datasets, while overall prediction accuracy remains largely unchanged, indicating that regional alignment can be obscured when summarizing across the brain.
arXiv AI
Oct 9
Predicting Alignment Generalization with Value Representations
The paper introduces the task of predicting alignment generalization, which measures how fine‑tuning a language model to follow a specific value affects its behavior across a broad set of other values. Through a large‑scale study of 66 values, the authors show that representations derived from model activations when applying values in context outperform textual description‑based methods, achieving a correlation of 0.45 versus 0.05. They further demonstrate that these representations can predict downstream robustness and help construct a taxonomy of LLM values based on empirical generalization dynamics.
arXiv Computation and Language
Sep 11
Cross-lingual brain-language model alignment is robust but challenges hierarchical and computational accounts
The study examined whether brain-language model alignment reflects shared computational mechanisms or merely stable lexical‑semantic correspondences. Using whole‑brain encoding across Mandarin, English, and French, transformer representations predicted activity in a distributed network that overlapped across languages and remained stable across layers. Contextual embeddings and measures of prediction or compression did not outperform static lexical embeddings, suggesting that alignment is robust but not informative about shared computational processes.
arXiv AI
Oct 16
Decomposing Brain-LLM Alignment with Interpretable Semantic Representations
The study investigates how a large language model (LLaMA2‑7B) aligns with human brain activity during naturalistic language comprehension by using SCRIBE, an interpretable semantic representation of 65 neurocognitively grounded properties. Variance partitioning on fMRI data from seven participants reveals that shared variance between LLaMA2‑7B and SCRIBE dominates across the brain, yet both representations also contribute unique variance. Further analysis shows that concrete semantic properties correlate more strongly with shared variance, while abstract properties do not show increased unique variance, and ablation experiments demonstrate that multiple semantic dimensions cumulatively influence both shared and unique brain-predictive variance.
arXiv AI
Jul 21
What Makes Linguistic Representations Good Models of High-Level Visual Perception in the Human Brain?
arXiv:2607. 16214v1 Announce Type: cross Abstract: Image descriptions represented with language models (LMs) predict human brain responses to naturalistic images in high-level visual regions, but the factors driving this predictivity remain unclear.