SMMD loss combines MMD with numeric distance kernels and smoothness to improve accuracy on mathematical reasoning, arithmetic, clock recognition, and chart QA across LLMs and VLMs.
Self-alignment pretraining for biomedical entity representations
4 Pith papers cite this work, alongside 1,698 external citations. Polarity classification is still indexing.
4
Pith papers citing it
1,698
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
The method aggregates multiple hallucination evaluation scores via conformal p-values to enable calibrated detection with controlled false alarm rates across LLMs and datasets.
A graph-based framework learns a shared semantic space for EHR data harmonization by integrating site-specific summaries, biomedical knowledge graphs, and LLM semantics, evaluated across seven institutions in two languages.
CRITIC improves LLM outputs on question answering, math synthesis, and toxicity reduction by having the model interact with tools to critique and revise its initial generations.
citing papers explorer
-
Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment
SMMD loss combines MMD with numeric distance kernels and smoothness to improve accuracy on mathematical reasoning, arithmetic, clock recognition, and chart QA across LLMs and VLMs.
-
Principled Detection of Hallucinations in Large Language Models via Multiple Testing
The method aggregates multiple hallucination evaluation scores via conformal p-values to enable calibrated detection with controlled false alarm rates across LLMs and datasets.
-
Representation learning to advance multi-institutional studies with electronic health record data from US and France
A graph-based framework learns a shared semantic space for EHR data harmonization by integrating site-specific summaries, biomedical knowledge graphs, and LLM semantics, evaluated across seven institutions in two languages.
-
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
CRITIC improves LLM outputs on question answering, math synthesis, and toxicity reduction by having the model interact with tools to critique and revise its initial generations.