Search papers, labs, and topics across Lattice.
3
0
4
3
RuleChef transforms LLM-generated task knowledge into human-editable rules, enhancing transparency and adaptability in NLP applications.
Span-level hallucination detection can now effectively address structured inputs like code and tool outputs, not just natural language, revealing a critical gap in current RAG evaluations.
A 150M-parameter ModernBERT classifier outperforms leading LLMs in extractive question answering, achieving a significant accuracy boost for academic research.
