Search papers, labs, and topics across Lattice.
3
0
7
3
Manipulating just a few sparse neurons can steer Arabic LLMs to generate dialect-specific outputs without the need for extensive fine-tuning.
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.
