APCD adaptively branches LLM decoding paths based on token entropy and contrasts divergent paths to improve factual accuracy while preserving efficiency.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2representative citing papers
Infherno deploys LLM agents with code execution and terminology tools to synthesize FHIR resources from unstructured clinical notes, matching human baseline performance on synthetic and real datasets.
citing papers explorer
-
APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation
APCD adaptively branches LLM decoding paths based on token entropy and contrasts divergent paths to improve factual accuracy while preserving efficiency.
-
Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes
Infherno deploys LLM agents with code execution and terminology tools to synthesize FHIR resources from unstructured clinical notes, matching human baseline performance on synthetic and real datasets.