3 papers
cs.CL2025
ICLR: In-Context Learning of Representations
Core Francisco Park, Andrew Lee, Ekdeep Singh Lubana +5
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…
cs.LG2024
Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
Kento Nishi, Rahul Ramesh, Maya Okawa +3
Knowledge Editing (KE) algorithms alter models' weights to perform targeted updates to incorrect, outdated, or otherwise unwanted factual associations. However, recent work has sho…
cs.LG2024
Swing-by Dynamics in Concept Learning and Compositional Generalization
Yongyi Yang, Core Francisco Park, Ekdeep Singh Lubana +3
Prior work has shown that text-conditioned diffusion models can learn to identify and manipulate primitive concepts underlying a compositional data-generating process, enabling gen…