A modular pipeline combines structured patient generation, journey simulation, and LLM note generation with validation to produce a released dataset of 70 synthetic patients each with 20-50 longitudinal clinical notes.
Hallucination mitigation using agentic ai natural language- based frameworks
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.AI 4years
2026 4representative citing papers
MADP multi-agent pipeline with human-in-the-loop achieves 97% full automation on 955 real documents, 98.5% accuracy on ablation set, and 69-70% reductions in FTE, energy, and emissions versus manual processing.
In kinship-dominant agent swarms, adding logical agents increases stability of erroneous trajectories, leading to logic saturation with zero internal entropy but unit factual error.
Three-stage agentic review pipeline with semantic caching reduces Total Hallucination Score by 31-36% and LLM calls by 47% on a custom 310-prompt benchmark.
citing papers explorer
-
A Pipeline for Generating Longitudinal Synthetic Clinical Notes Using Large Language Models
A modular pipeline combines structured patient generation, journey simulation, and LLM note generation with validation to produce a released dataset of 70 synthetic patients each with 20-50 longitudinal clinical notes.
-
MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop
MADP multi-agent pipeline with human-in-the-loop achieves 97% full automation on 955 real documents, 98.5% accuracy on ablation set, and 69-70% reductions in FTE, energy, and emissions versus manual processing.
-
The Inverse-Wisdom Law: Architectural Tribalism and the Consensus Paradox in Agentic Swarms
In kinship-dominant agent swarms, adding logical agents increases stability of erroneous trajectories, leading to logic saturation with zero internal entropy but unit factual error.
-
Hallucination Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching
Three-stage agentic review pipeline with semantic caching reduces Total Hallucination Score by 31-36% and LLM calls by 47% on a custom 310-prompt benchmark.