Perspective independence, more than personas, drives LLM teams - and where they reverse
Feng, J.; Jiao, Y.; Li, Y.; Xie, L.; Peng, W.; Sun, X.
Show abstract
Multi-agent prompting of large language models has produced contradictory diagnostic results, and it remains unclear whether any benefit comes from specialist personas or from perspective independence. We compared a single direct call, five personas in one context, and the same five roles as isolated agents integrated by a moderator, with five repeat runs per case, on 87 CPC cases, 406 MedCaseReasoning cases, and 364 emergency department encounters, under an LLM judge validated against clinicians. On the external benchmark the team beat the single call on both pre-specified recall endpoints (top-3 +3.0 points, p = 0.0079; top-5 +3.9, p = 3.8 x 10^-5;); a factorial attributes the gain to independent generation plus moderated synthesis, not the specialist roles. On real emergency presentations the benefit reversed (top-1 40.1% versus 34.3%, p < 0.0001), carried by the specialist role lists and surviving added objective results. Deployment should key on the question and the input at hand.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Robust Disease Prognosis via Diagnostic Knowledge Preservation: A Sequential Learning Approach 89%
- Comparison of local large language models for extraction of signs and symptoms data from electronic health records 88%
- Investigating the Role of AI Explanations in Lay Individuals’ Comprehension of Radiology Reports: A Metacognition Lense 88%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.