Search papers, labs, and topics across Lattice.
3
0
7
3
Manipulating just a few neurons can transform Arabic LLM outputs from Modern Standard Arabic to specific dialects, revealing a surprising level of control over dialectal generation.
Visualizing counterfactuals can unlock reasoning capabilities in LLMs that text alone cannot achieve.
Despite its simplicity, mean pooling works surprisingly well because modern text encoders concentrate token embeddings, preserving crucial information about their distribution.
