Search papers, labs, and topics across Lattice.
University of South Florida, Tampa, Florida, USA
2
0
3
3
Implicit reasoning steering can covertly amplify latent biases in language models, shifting their predictions through seemingly innocuous text.
Unstructured pruning isn't just about shrinking LLMs; it can actually *boost* their reasoning abilities during test-time scaling, outperforming even the full, unpruned models.
