Search papers, labs, and topics across Lattice.
3
0
6
Ambiguity in natural language queries can be resolved autonomously, boosting SQL execution accuracy by over 13% without human intervention.
Contamination in NL2SQL benchmarks can inflate LLM accuracy, but SPENCE reveals that newer datasets are largely free from this bias.
Get 80% of your prompt length back without sacrificing accuracy using a diffusion-based pruning method that can mask multiple tokens at once.
