Getting aligned on representational alignment
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 9 Pith papers
-
Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
In navigation tasks, DQN learns MDP-homomorphism-invariant representations while PPO learns action-symmetric ones despite comparable performance, with effects on transfer and in LLMs.
-
Capability $\neq$ Interpretability: Human Interpretability of Vision Foundation Models
Foundation models yield less human-interpretable features than supervised vision transformers, with interpretability tied to activation locality and coarse semantic alignment rather than task performance.
-
An Experimental Method to Study Opinion Diffusion in Human-AI Hybrid Societies
Hybrid human-AI networks in 5x5 grids reached lower final polarization than human-only networks after eight rounds of opinion revision on polarizing topics.
-
Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment
A human-centered OOD spectrum based on perceptual difficulty shows vision-language models align best with human errors across regimes, with CNNs stronger on near-OOD and ViTs on far-OOD.
-
The Attentional White Bear Effect in Transformer Language Models
Prohibited concepts remain recoverable from hidden states, influence attention routing, and shape generations in transformers under instruction-based suppression.
-
Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners
Frontier LRMs match human game-learning behavior and predict fMRI signals an order of magnitude better than RL or Bayesian agents because of their in-context game-state representations.
-
Emergent Symbolic Structure in Health Foundation Models: Extraction, Alignment, and Cross-Modal Transfer
Health foundation model embeddings contain an interpretable symbolic organization shared across modalities that supports cross-domain transfer without joint training.
-
Non-identifiability of Explanations from Model Behavior in Deep Networks of Image Authenticity Judgments
Models predicting human authenticity judgments produce inconsistent attribution maps across architectures, showing that explanations are non-identifiable.
-
Representation learning from OCT images
A structured survey of representation learning methods for retinal OCT image analysis, covering supervised, self-supervised, generative, multimodal, and foundation model approaches along with datasets and open problems.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.