HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
arXiv preprint arXiv:2402.13669 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
A pipeline generates CoT traces that reduce causal hallucination in small LLMs on event causality tasks, paired with a new Causal Hallucination Rate metric that guides and validates the process.
FedSDR augments federated self-distillation with dual LoRA streams (local smoothing and global rectification) to produce globally aligned, factually faithful models under statistical heterogeneity.
Introduces Tree Generation (TG-SFT) to generate synthetic instruction-tuning data from LLMs, reducing catastrophic forgetting when fine-tuning MLLMs on domain-specific or multimodal data.
citing papers explorer
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
-
Generating Effective CoT Traces for Mitigating Causal Hallucination
A pipeline generates CoT traces that reduce causal hallucination in small LLMs on event causality tasks, paired with a new Causal Hallucination Rate metric that guides and validates the process.
-
FedSDR: Federated Self-Distillation with Rectification
FedSDR augments federated self-distillation with dual LoRA streams (local smoothing and global rectification) to produce globally aligned, factually faithful models under statistical heterogeneity.
-
Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression
Introduces Tree Generation (TG-SFT) to generate synthetic instruction-tuning data from LLMs, reducing catastrophic forgetting when fine-tuning MLLMs on domain-specific or multimodal data.