RePrompT uses recurrent prompt tuning to inject prior-visit latent states and cohort-derived population prompt tokens into LLMs, yielding better performance than pure EHR or pure LLM baselines on MIMIC clinical prediction tasks.
arXiv preprint arXiv:2406.08660 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
support 1representative citing papers
LabelPigeon jointly performs translation and label projection via XML tags, improving translation quality in 11 languages and cross-lingual transfer by up to +40.2 F1 on NER across 27 languages.
Targeted prompting and system interventions enable local LLMs such as Llama 3.1 70B to exploit 83% of tested Linux privilege escalation vulnerabilities.
Poodle shows that LLMs can be automatically replaced with cheaper models for recurring tasks to save significant cost and energy without extra user effort.
citing papers explorer
-
RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models
RePrompT uses recurrent prompt tuning to inject prior-visit latent states and cohort-derived population prompt tokens into LLMs, yielding better performance than pure EHR or pure LLM baselines on MIMIC clinical prediction tasks.
-
Just Use XML: Revisiting Joint Translation and Label Projection
LabelPigeon jointly performs translation and label projection via XML tags, improving translation quality in 11 languages and cross-lingual transfer by up to +40.2 F1 on NER across 27 languages.
-
Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents
Targeted prompting and system interventions enable local LLMs such as Llama 3.1 70B to exploit 83% of tested Linux privilege escalation vulnerabilities.
-
Poodle: Seamlessly Scaling Down Large Language Models with Just-in-Time Model Replacement
Poodle shows that LLMs can be automatically replaced with cheaper models for recurring tasks to save significant cost and energy without extra user effort.