MAC framework selects Pareto-optimal LLM agents and masks low cross-consistency outputs for adaptive collaboration in medical decision-making.
Binary codes capable of correcting deletions, insertions, and reversals
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Set-level data entropy estimators show linear correlation with LLM memorization scores, forming the Entropy-Memorization Linearity.
citing papers explorer
-
MAC: Masked Agent Collaboration Boosts Large Language Model Medical Decision-Making
MAC framework selects Pareto-optimal LLM agents and masks low cross-consistency outputs for adaptive collaboration in medical decision-making.
-
Data Compressibility Quantifies LLM Memorization
Set-level data entropy estimators show linear correlation with LLM memorization scores, forming the Entropy-Memorization Linearity.
- MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing