REVIEW 10 cited by
Getting aligned on representational alignment
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the similarity between the representations formed by these diverse systems? Do similarities in representations then translate into similar behavior? If so, then how can a system's representations be modified to better match those of another system? These questions pertaining to the study of representational alignment are at the heart of some of the most promising research areas in contemporary cognitive science, neuroscience, and machine learning. In this Perspective, we survey the exciting recent developments in representational alignment research in the fields of cognitive science, neuroscience, and machine learning. Despite their overlapping interests, there is limited knowledge transfer between these fields, so work in one field ends up duplicated in another, and useful innovations are not shared effectively. To improve communication, we propose a unifying framework that can serve as a common language for research on representational alignment, and map several streams of existing work across fields within our framework. We also lay out open problems in representational alignment where progress can benefit all three of these fields. We hope that this paper will catalyze cross-disciplinary collaboration and accelerate progress for all communities studying and developing information processing systems.
Forward citations
Cited by 10 Pith papers
-
Beyond Color Geometry: Evaluating Human-Like Color Representations in Vision Models
MAE encoders show significantly stronger alignment with human fuzzy color categories than other ViTs, beyond what perceptual color geometry explains.
-
Accuracy Does Not Guarantee Human-Likeness: Cross-Domain Human-Centered Benchmark in Monocular Depth Estimation
Across 69 monocular depth estimators, human-likeness of error patterns peaks near human-level accuracy and declines for the most accurate models: accuracy does not guarantee human-like depth perception.
-
The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold
Post-memorization learning in grokking is equivalent to minimizing the weight norm on the zero-loss manifold, with a closed-form approximation for two-layer networks.
-
Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an Example
At matched task accuracy, e-prop trained RNNs reach neural data similarity comparable to BPTT trained RNNs on Mante 2013 and Sussillo 2015 datasets, with initialization and architecture influencing similarity more tha...
-
The Principle of Isomorphism: A Theory of Population Activity in Grid Cells and Beyond
Grid-cell population activity is toroidal because path integration and the neural metric both require a compact flat/commutative structure, and hexagonal single-cell fields emerge only in a narrow range of torus sizes.
-
Linear Spatial World Models Emerge in Large Language Models
Spatial relation words in LLaMA and Qwen models form antipodal, roughly orthogonal directions in a low-dimensional subspace, and steering along these directions changes the model's output.
-
Using LLMs to Advance the Cognitive Science of Collectives
A position paper arguing that LLMs can help cognitive scientists study collective behavior along structural, interactional, and individual complexity axes, with cautions about bias and reproducibility.
-
Evaluating Steering Techniques using Human Similarity Judgments
Prompt-based steering outperformed activation-based steering on accuracy, but no method produced representations well aligned with human judgments, especially for size.
-
The Representational Alignment between Humans and Language Models is implicitly driven by a Concreteness Effect
For 40 German nouns, human similarity judgments and language model embeddings align mainly because both are organized along the concreteness dimension, not along frequency, length, or orthographic similarity.
-
Representation biases: will we achieve complete understanding by analyzing representations?
Feature representation biases in trained models can distort PCA, regression, RSA, and model-brain comparisons, so representational analyses may not reveal all of a system's computations.
Discussion (0). Sign in to comment.