Search papers, labs, and topics across Lattice.
Affiliation:
6
0
8
AI agents can now build and reuse persistent, artifact-specific knowledge, dramatically improving their ability to find relevant information for complex tasks and reducing operational costs.
LLMs struggle with procedural database programming, revealing critical gaps in their capabilities that traditional benchmarks overlook.
ConflictScore reveals that language models often overlook conflicting evidence, leading to overconfident and inaccurate claims.
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.
