mlsanityData to 14 Oct 2026

Causes and Consequences of Representational Similarity in Machine Learning Models

arXiv 2505.13899 ↗First posted 20 May 2025cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Numerous works have noted similarities in how machine learning models represent the world, even across modalities. Although much effort has been devoted to uncovering properties and metrics on which these models align, surprisingly little work has explored causes of this similarity. To advance this line of inquiry, this work explores how two factors - dataset overlap and task overlap - influence downstream model similarity. We evaluate the effects of both factors through experiments across model sizes and modalities, from small classifiers to large language models. We find that both task and dataset overlap cause higher representational similarity and that combining them provides the strongest effect. Finally, we consider downstream consequences of representational similarity, demonstrating how greater similarity increases vulnerability to transferable adversarial and jailbreak attacks.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 38 of its 54 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

38 of 54 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2020Scaling Laws for Neural Language Modelscited by 6,586
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  7. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  8. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  10. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  11. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,420
  12. 2023A Comprehensive Overview of Large Language Modelscited by 648
26 more
  1. 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Modelscited by 536
  2. 2024Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attackscited by 486
  3. 2019On the Efficacy of Knowledge Distillationcited by 381
  4. 2018Insights on representational similarity in neural networks with canonical correlationcited by 324
  5. 2020Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depthcited by 245
  6. 2015Convergent Learning: Do different neural networks learn the same representations?cited by 220
  7. 2021Revisiting Model Stitching to Compare Neural Representationscited by 209
  8. 2022Relative representations enable zero-shot latent space communicationcited by 191
  9. 2021Towards Understanding Knowledge Distillationcited by 158
  10. 2023Similarity of Neural Network Models: A Survey of Functional and Representational Measurescited by 131
  11. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 129
  12. 2020What shapes feature representations? Exploring datasets, architectures, and trainingcited by 126
  13. 2020On Linear Identifiability of Learned Representationscited by 105
  14. 2024Universal Neurons in GPT2 Language Modelscited by 102
  15. 2020Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Datacited by 87
  16. 2020Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistencycited by 78
  17. 2019Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasetscited by 56
  18. 2024Jamba-1.5: Hybrid Transformer-Mamba Models at Scalecited by 50
  19. 2023Rosetta Neurons: Mining the Common Units in a Model Zoocited by 46
  20. 2025We're Different, We're the Same: Creative Homogeneity Across LLMscited by 42
  21. 2024AI and the Problem of Knowledge Collapsecited by 34
  22. 2023Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Modelcited by 19
  23. 2024On Large Language Models in National Security Applicationscited by 19
  24. 2024Objective drives the consistency of representational similarity across datasetscited by 18
  25. 2023Towards Measuring Representational Similarity of Large Language Modelscited by 6
  26. 2021Divergent representations of ethological visual inputs emerge from supervised, unsupervised, and reinforcement learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoningcited by 3
  2. 2026Representation Alignment Rests on Linear Structurecited by 1
  3. 2026AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024What Makes Two Language Models Think Alike?
  2. 2026The Triangle of Similarity: A Multi-Faceted Framework for Comparing Neural Network Representations
  3. 2026Divergent large language model predictions from convergent representations in ambiguous word pairs
  4. 2026A Unifying Framework for Concept-Based Representational Similarity
  5. 2025Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed
  6. 2026Representational Similarity and Model Behavior in Multi-Agent Interaction
  7. 2025Jailbreak Transferability Emerges from Shared Representations
  8. 2024Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity