Search papers, labs, and topics across Lattice.
6
0
10
Routing attribution reveals that the choice of data views can dramatically influence model interpretability, even when performance gains are minimal.
CalVerT boosts QA performance by equipping agents with calibrated self-confidence and grounding scores, reducing both erroneous confident answers and unnecessary information retrieval.
Knowledge graphs can dramatically improve the reliability of conversational AI for vulnerable populations, outperforming standard search engines in providing accurate, context-aware information about community services.
LLMs in medical diagnosis are alarmingly prone to jumping to conclusions, often answering before seeing all the evidence, but strategically delaying the question and evidence presentation can boost accuracy by up to 62.6%.
LLMs can automate and improve thematic analysis of qualitative data, achieving expert-level alignment in clinical domains through iterative codebook refinement.
PathMoE reveals the specific modality interactions driving individual predictions in pediatric brain tumor classification, offering crucial interpretability for rare tumor subtypes.
