Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
1
0
2
0
This work builds a standardized harness over four clinical practice guidelines and evaluates twelve LLMs on 222 synthetic clinical questions, finding that most models can attach verbatim quotes to over 90% of their claims from prompting alone, apart from some lightweight models such as claude-haiku-4.5.