Search papers, labs, and topics across Lattice.
3
0
5
1
RuleChef transforms LLM-generated task knowledge into human-editable rules, enhancing transparency and adaptability in NLP applications.
A 150M-parameter ModernBERT classifier outperforms leading LLMs in extractive question answering, achieving a significant accuracy boost for academic research.
Coding agents can achieve higher recall and F1 scores by selectively attending to just 8% of tool output tokens, rather than processing the entire observation.
