mlsanityData to 7 Oct 2026

Getting aligned on representational alignment

arXiv 2310.13018 ↗First posted 18 Oct 2023q-bio.NC cs.AI cs.LGcited by 142

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 142 papers in the map (data through 7 Oct 2026). Builds on 147 of its 351 references that are in the map. First posted on arXiv 18 Oct 2023.

Builds on

147 of 351 references.

References · 147

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  10. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  11. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  12. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
38 more
  1. 2017Deep reinforcement learning from human preferencescited by 3,846
  2. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  3. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  4. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  5. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  6. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  7. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  8. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  9. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  10. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  11. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  12. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  13. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  14. 2020Concept Bottleneck Modelscited by 1,022
  15. 2019When Does Label Smoothing Help?cited by 985
  16. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 966
  17. 2019Relational Knowledge Distillationcited by 873
  18. 2023Progress measures for grokking via mechanistic interpretabilitycited by 822
  19. 2016Sequence-Level Knowledge Distillationcited by 761
  20. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  21. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  22. 2019Contrastive Representation Distillationcited by 734
  23. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  24. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  25. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  26. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  27. 2019Similarity-Preserving Knowledge Distillationcited by 507
  28. 2018Behavioral Cloning from Observationcited by 482
  29. 2020Artificial Intelligence, Values and Alignmentcited by 443
  30. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 438
  31. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  32. 2019On the Efficacy of Knowledge Distillationcited by 377
  33. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
  34. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  35. 2018Insights on representational similarity in neural networks with canonical correlationcited by 318
  36. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 286
  37. 2023Generating Images with Multimodal Language Modelscited by 259
  38. 2019Risks from Learned Optimization in Advanced Machine Learning Systemscited by 250

50 most cited of 147 All 147 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 44; 2025: 46; 2026: 49.

142 papers.

Sort:

By area:

  1. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 415
  2. 2024The Platonic Representation Hypothesiscited by 362
  3. 2024MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Datacited by 105
  4. 2024Building Machines that Learn and Think with Peoplecited by 73
  5. 2025Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignmentcited by 62
  6. 2024Emergence of a High-Dimensional Abstraction Phase in Language Transformerscited by 56
  7. 2024Knowledge Mechanisms in Large Language Models: A Survey and Perspectivecited by 50
  8. 2025We're Different, We're the Same: Creative Homogeneity Across LLMscited by 41
  9. 2024Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoderscited by 25
  10. 2024Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Functioncited by 24
  11. 2025On Benchmarking Human-Like Intelligence in Machinescited by 24
  12. 2024Learned feature representations are biased by complexity, learning order, position, and morecited by 22
38 more
  1. 2024Dimensions underlying the representational alignment of deep neural networks with humanscited by 22
  2. 2026There Will Be a Scientific Theory of Deep Learningcited by 21
  3. 2024Psychometric Alignment: Capturing Human Knowledge Distributions via Language Modelscited by 18
  4. 2024ReSi: A Comprehensive Benchmark for Representational Similarity Measurescited by 18
  5. 2024When Does Perceptual Alignment Benefit Vision Representations?cited by 18
  6. 2024What Representational Similarity Measures Imply about Decodable Informationcited by 18
  7. 2024Correcting Biased Centered Kernel Alignment Measures in Biological and Artificial Neural Networkscited by 16
  8. 2023Duality of Bures and Shape Distances with Implications for Comparing Neural Representationscited by 14
  9. 2024Quantifying Knowledge Distillation Using Partial Information Decompositioncited by 12
  10. 2024Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neurosciencecited by 11
  11. 2024Evaluating Representational Similarity Measures from the Lens of Functional Correspondencecited by 11
  12. 2024Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformerscited by 11
  13. 2024Differentiable Optimization of Similarity Scores Between Models and Brainscited by 10
  14. 2025Levels of Analysis for Large Language Modelscited by 9
  15. 2024Towards Building Specialized Generalist AI with System 1 and System 2 Fusioncited by 8
  16. 2025The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifoldcited by 8
  17. 2023Learning Human-like Representations to Enable Learning Human Valuescited by 7
  18. 2024Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Featurescited by 7
  19. 2024Dreaming to Assist: Learning to Align with Human Objectives for Shared Control in High-Speed Racingcited by 7
  20. 2025Human-Aligned Image Models Improve Visual Decoding from the Braincited by 7
  21. 2025StickMotion: Generating 3D Human Motions by Drawing a Stickmancited by 7
  22. 2025Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spacescited by 6
  23. 2025A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.icited by 6
  24. 2025Using LLMs to Advance the Cognitive Science of Collectivescited by 6
  25. 2025Representation biases: will we achieve complete understanding by analyzing representations?cited by 6
  26. 2025Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamplescited by 6
  27. 2026Differential syntactic and semantic encoding in LLMscited by 6
  28. 2024An Analysis of Human Alignment of Latent Diffusion Modelscited by 5
  29. 2024Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neurosciencecited by 5
  30. 2024Constructive Approach to Bidirectional Influence between Qualia Structure and Language Emergencecited by 5
  31. 2024Probing the contents of semantic representations from text, behavior, and brain data using the psychNorms metabasecited by 5
  32. 2025Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shiftscited by 5
  33. 2025Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representationscited by 5
  34. 2025Position: We Need An Algorithmic Understanding of Generative AIcited by 5
  35. 2024Investigating Representation Universality: Case Study on Genealogical Representationscited by 4
  36. 2025Linear Spatial World Models Emerge in Large Language Modelscited by 4
  37. 2025When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspectivecited by 4
  38. 2025Language models align with brain regions that represent concepts across modalitiescited by 4

50 most cited of 142 All 142 (JSON)