ReElicit uses LLMs to elicit adaptive feature embeddings for Gaussian process Bayesian optimization of system prompts under aggregate-only feedback, outperforming baselines across ten tasks with a 30-evaluation budget.
hub
International conference on machine learning , pages=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 11roles
method 1polarities
use method 1representative citing papers
Performance collapse in layer-pruned LLMs stems from disrupting the Silent Phase of decision-making, which blocks the transition to correct predictions, while the later Decisive Phase is robust to pruning.
Introduces the Indic-CodecFake dataset for Indic codec deepfakes and SATYAM, a novel hyperbolic ALM that outperforms baselines through dual-stage semantic-prosodic fusion using Bhattacharya distance.
Introduces LOES, a constructive spectral method to select task-discriminative subspaces from intermediate layer embeddings, and GeoReg for enforcing simplicial class geometry during fine-tuning, with reported gains increasing with model depth across modalities.
Transformers are limited to a linearly growing number of accessible output sequences with prompt length, with exponential decay in accessible proportion beyond a critical point, even under unbounded context.
PIMSM is a Mamba-based architecture that maps knee frequencies from spectra to multi-scale discretization parameters to reduce representation drift under distribution shifts in fMRI and weather forecasting.
PrivUn shows privacy unlearning in LLMs produces gradient-driven ripple effects and only shallow forgetting across layers, with new strategies proposed for deeper removal.
MER-DG applies modality-entropy regularization to reduce fusion overfitting in multimodal domain generalization, reporting average gains of 5% over standard fusion and 2% over prior methods on EPIC-Kitchens and HAC benchmarks.
Representations learned by large AI models are converging toward a shared statistical model of reality.
TopoGeoScore learns a non-negative linear combination of geometric and topological features from source embeddings via self-supervised invariance to select robust checkpoints for OOD scenarios.
A mechanics of the learning process is emerging in deep learning theory, characterized by dynamics, coarse statistics, and falsifiable predictions across idealized settings, limits, laws, hyperparameters, and universal behaviors.
citing papers explorer
-
Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Prompts
ReElicit uses LLMs to elicit adaptive feature embeddings for Gaussian process Bayesian optimization of system prompts under aggregate-only feedback, outperforming baselines across ten tasks with a 30-evaluation budget.