Adaptive Instruction Composition uses a neural contextual bandit with RL to adaptively combine crowdsourced texts, generating more effective and diverse LLM jailbreaks than random or prior adaptive methods on Harmbench.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
SPENDER autoencoder plus k-d tree nearest-neighbor classification on DESI spectra identifies AGN and broad-line AGN at accuracies 0.952 and 0.965, recovering sources missed by single-line diagnostics.
CLIC encodes patient context and technical metadata as natural language text to boost ECG-based cardiac pathology classification performance over signal-only models.
RAG and topic-based word selection increase perceived political relevance in generated satirical definitions but produce no clear improvement in humor according to human raters.
citing papers explorer
-
Adaptive Instruction Composition for Automated LLM Red-Teaming
Adaptive Instruction Composition uses a neural contextual bandit with RL to adaptively combine crowdsourced texts, generating more effective and diverse LLM jailbreaks than random or prior adaptive methods on Harmbench.
-
Beyond traditional emission-line diagnostics: using autoencoders to uncover active galactic nuclei in DESI spectra
SPENDER autoencoder plus k-d tree nearest-neighbor classification on DESI spectra identifies AGN and broad-line AGN at accuracies 0.952 and 0.965, recovering sources missed by single-line diagnostics.
-
CLIC: Contextual Language-Informed Cardiac Pathology Classification
CLIC encodes patient context and technical metadata as natural language text to boost ECG-based cardiac pathology classification performance over signal-only models.
-
Grounded Satirical Generation with RAG
RAG and topic-based word selection increase perceived political relevance in generated satirical definitions but produce no clear improvement in humor according to human raters.