ICLR: In-Context Learning of Representations

This is experimental HTML to improve accessibility. We invite you to report rendering errors. Use Alt+Y to toggle on accessible reporting links and Alt+Shift+Y to toggle off. Learn more about this project and help improve conversions. Recent work has demonstrated that semantics specified by pretraining data influence how representations of different concepts are organized in a large language model (LLM). However, given the open-ended nature of LLMs, e.g., their ability to in-context learn, we can ask whether models alter these pretraining semantics to adopt alternative, context-specified ones. Specifically, if we provide in-context exemplars wherein a concept plays a different role than what the pretraining data suggests, do models reorganize their representations in accordance with these novel semantics? To answer this question, we take inspiration from the theory of conceptual role semantics and define a toy “graph tracing” task wherein the nodes of the graph are referenced via conc

ICLR: In-Context Learning of Representations Core Francisco Park 1,2,3 , Andrew Lee ∗4 , Ekdeep Singh Lubana ∗1,3 , Yongyi Yang ∗1,3,5 , Maya Okawa 1,3 , Kento Nishi 1,4 , Martin Wattenberg 4 , & Hidenori Tanaka 1,3 1 CBS-NTT Program in Physics of Intelligence, Harvard University 2 Department of Physics, Harvard University 3 Physics & Informatics Lab, NTT Research Inc. 4 SEAS, Harvard University 5 CSE, University of Michigan, Ann Arbor Equal contribution. Contact: {corefranciscopark,andrewlee}@g.harvard.edu , yongyi@umich.edu , {ekdeeplubana, hidenori_tanaka}@fas.harvard.edu . Abstract Recent

related reading

• Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
• In-context Learning and Induction Headstransformer-circuits.pub
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• In-context learning creates task vectorsarxiv.org
• [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
• How does in-context learning work? A framework for understanding the differences from traditional supervised learning | SAIL Blogai.stanford.edu
• Are Emergent Abilities in Large Language Models just In-Context Learning?arxiv.org
• Learning without training: The implicit dynamics of in-context learningarxiv.org
• [2506.06266] Cartridges: Lightweight and general-purpose long context representations via self-studyarxiv.org
• In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Explorationarxiv.org
• Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?arxiv.org
• [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org