Search papers, labs, and topics across Lattice.
3
0
3
Predictive turn-taking in sign language interactions reveals that hand cues significantly enhance SHIFT/HOLD predictions, but SHIFT remains elusive.
Recall-based prompting can dramatically improve LLM performance on knowledge cutoff tasks, especially for counterfactual queries.
Reversing input text can unlock hidden contextual information, leading to richer embeddings and substantial performance gains in training-free LLMs.
