Representation Geometry in Language Models

Ask about this topic

Overview

This field studies the shapes and relationships formed by token embeddings and hidden activations, and how those structures change across layers, contexts, and training. Researchers use linear probes, representational similarity analysis, spectral and manifold methods, sparse autoencoders, and causal interventions such as activation patching and steering. These tools are applied to questions about reasoning, multilingual transfer, retrieval, safety, and reliability, using settings that range from controlled synthetic tasks to benchmarks such as GSM8K and MTEB. A central open tension is that information being decodable or geometrically similar does not guarantee that a model uses it causally; useful structure may also be local, nonlinear, or sensitive to measurement choices.

Latest papers

CardsList

417 papers78 papers in the last four weeks, up 34% on the four weeks before. 0.5% of all new papers.

  1. Stream separation improves Bregman conditioning in transformers

    Mar 22, 2026James Clayton KerceTransformerRepresentation Geometry in Language Models

    Georgia Tech Research Institute

  2. Semantic Sections: An Atlas-Native Feature Ontology for Obstructed Representation Spaces

    Mar 21, 2026Hossein JavidniaMechanistic InterpretabilityRepresentation Geometry in Language Models

    School of Computing, Dublin City University, Ireland

  3. Weber's Law in Transformer Magnitude Representations: Efficient Coding, Representational Geometry, and Psychophysical Laws in Language Models

    Mar 21, 2026Jon-Paul CacioliRepresentation Geometry in Language ModelsNumerical Reasoning in Language Models

    Independent Researcher, Melbourne Australia

  4. Thinking in Different Spaces: Domain-Specific Latent Geometry Survives Cross-Architecture Translation

    Mar 20, 2026Marcus Armstrong, Navid Ayoobi, Arjun MukherjeeRepresentation Geometry in Language ModelsActivation Steering

    Department of Computer Science, University of Houston, Houston, TX 77204

  5. GeoLAN: Geometric Learning of Latent Explanatory Directions in Large Language Models

    Mar 19, 2026Tianyu Bell Pan, Damon L. WoodardLLM InterpretabilityRepresentation Geometry in Language Models

    Department of Electrical and Computer Engineering Florida Institute for National Security Applied Artificial Intelligence Group University of Florida

  6. Ventriloquist LLMs: Linear Alignment of Late-Stage Representations

    Mar 19, 2026Matt Gorbett, Suman JanaLatent Space AlignmentLLM Alignment

    Capital One New York, NY 10003, USA · Department of Computer Science Columbia University New York, NY 10027, USA

  7. Pretrained Multilingual Transformers Reveal Quantitative Distance Between Human Languages

    Mar 18, 2026Yue Zhao, Jiatao Gu, Paloma Jeretič +1Representation Geometry in Language Models

    Institute for Functional Intelligent Materials, National University of Singapore. · Department of Computer and Information Science, University of Pennsylvania. · Department of Linguistics, University of Pennsylvania. +1

  8. Latent Semantic Manifolds in Large Language Models

    Mar 17, 2026Mohamed A. MabrokRepresentation Geometry in Language ModelsInformation Geometry

    Department of Mathematics and Statistics, Qatar University

  9. A Representation-Level Assessment of Bias Mitigation in Foundation Models

    Mar 17, 2026Svetoslav Nizhnichenkov, Rahul Nair, Elizabeth Daly +1Gender Bias in Language ModelsSocial Bias in Language Models

    IBM Research, Dublin, Ireland · School of Computer Science, University College Dublin, Dublin, Ireland

  10. Parametric Social Identity Injection and Diversification in Public Opinion Simulation

    Mar 17, 2026Hexi Wang, Yujia Zhou, Bangde Du +2Large Language Model-Based Social SimulationRepresentation Geometry in Language Models

    DCST, Tsinghua University Beijing, China · Quancheng Laboratory Jinan, Shandong, China

  11. Learning to Recall with Transformers Beyond Orthogonal Embeddings

    Mar 16, 2026Nuri Mert Vural, Alberto Bietti, Mahdi Soltanolkotabi +1TransformerMemorization in Language Models

    University of Toronto and Vector Institute · Flatiron Institute · University of Southern California +1

  12. The Illusion of Latent Generalization: Bi-directionality and the Reversal Curse

    Mar 13, 2026Julian Coda-Forno, Jane X. Wang, Arslan ChaudhryDecoder-Only Language ModelsMasked Language Modeling

    TUM, Helmholtz Munich · Google DeepMind

  13. CLaRE-ty Amid Chaos: Quantifying Representational Entanglement to Predict Ripple Effects in LLM Editing

    Mar 11, 2026Manit Baser, Alperen Yildiz, Dinil Mon Divakaran +1Language Model EditingRepresentation Geometry in Language Models

    National University of Singapore, Singapore · A*STAR Institute for Infocomm Research (A*STAR I2R), Singapore

  14. The Prediction-Measurement Gap: Toward Meaning Representations as Scientific Instruments

    Mar 10, 2026Hubert PlisieckiText EmbeddingsText Embedding Evaluation

    IDEAS Research Institute, Warsaw, Poland

  15. From Data Statistics to Feature Geometry: How Correlations Shape Superposition

    Mar 10, 2026Lucas Prieto, Edward Stevinson, Melih Barsbey +2Feature SuperpositionNeural Network Interpretability

  16. Think Before You Lie: How Reasoning Leads to Honesty

    Mar 10, 2026Ann Yuan, Asma Ghandeharioun, Carter Blum +6Deception in Language ModelsLLM Honesty

    Google DeepMind · Carnegie Mellon University · Harvard University

  17. Curveball Steering: The Right Direction To Steer Isn't Always Linear

    Mar 10, 2026Shivam Raval, Hae Jin Song, Linlin Wu +4Language Model SteeringActivation Steering

  18. One Language, Two Scripts: Probing Script-Invariance in LLM Concept Representations

    Mar 9, 2026Sripad KarneLLM InterpretabilitySparse Autoencoders

    Columbia University

  19. Whitening Reveals Cluster Commitment as the Geometric Separator of Hallucination Types

    Mar 8, 2026Matic KorunFeature WhiteningHallucination in Language Models

    Independent Researcher, Ljubljana, Slovenia

  20. A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs

    Mar 8, 2026Raghavv Goel, Risheek Garrepalli, Sudhanshu Agrawal +3Diffusion Language ModelsRepresentation Geometry in Language Models

    Qualcomm AI Research, Qualcomm Technologies Inc.

  21. NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks

    Mar 6, 2026Nandan Kumar Jha, Brandon ReagenTransformer FFNsNeural Network Training Dynamics

    New York University

  22. Navigating the Concept Space of Language Models

    Mar 6, 2026Wilson E. Marcílio-Jr, Danilo M. ElerLLM InterpretabilityRepresentation Geometry in Language Models

    Adaption Labs, Curitiba, PR, Brazil · São Paulo State University (UNESP), Presidente Prudente, SP, Brazil

  23. Sparse Crosscoders for diffing MoEs and Dense models

    Mar 6, 2026Marmik Chaudhari, Nishkal Hundia, Idhant GulatiMixture-of-Experts InterpretabilityMixture-of-Experts Models

    University of California, Berkeley · University of Maryland

  24. Feature Resemblance: Towards a Theoretical Understanding of Analogical Reasoning in Transformers

    Mar 5, 2026Ruichen Xu, Wenjing Yan, Ying-Jun Angela ZhangAnalogical ReasoningAnalogical Reasoning for Language Models

    Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong.

  25. Residual Stream Analysis of Overfitting And Structural Disruptions

    Mar 4, 2026Quan Liu, Han Zhou, Wenquan Wu +2Safety-Preserving Fine-Tuning of Language ModelsRefusal Behavior in Language Models

    BUPT · Baidu

  26. Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs

    Mar 3, 2026Mingyu Jin, Yutong Yin, Jingcheng Niu +7OOD GeneralizationRepresentation Geometry in Language Models

    Rutgers University · Northwestern University · UKP Lab, TU Darmstadt +3

  27. Tracing Pharmacological Knowledge In Large Language Models

    Mar 3, 2026Basil Hasan Khwaja, Dylan Chen, Guntas Toor +1LLM InterpretabilityRepresentation Geometry in Language Models

    School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA · Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA · Stephen J. R. Smith Faculty of Engineering and Applied Science, Queen’s University, Kingston, ON, Canada +1

  28. Understanding the Physics of Key-Value Cache Compression for LLMs through Attention Dynamics

    Mar 2, 2026Samhruth Ananthanarayanan, Ayan Sengupta, Tanmoy ChakrabortyAttention RoutingKV-Cache Compression

    IIT Delhi, India

  29. Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning

    Mar 1, 2026Hamed Damirchi, Ignacio Meza De la Jara, Ehsan Abbasnejad +3LLM InterpretabilityRepresentation Geometry in Language Models

    Australian Institute for Machine Learning, Adelaide University · Monash University · Concordia University

  30. The Lattice Representation Hypothesis of Large Language Models

    Mar 1, 2026Bo XiongSymbolic Reasoning in Language ModelsRepresentation Geometry in Language Models

    Stanford University, United States