ICL-derived intrinsic rewards are biased in general MDPs but asymptotically match true learning progress in non-temporal settings, with supporting experiments.
arXiv preprint arXiv:2311.00871 , year=
6 Pith papers cite this work, alongside 8 external citations. Polarity classification is still indexing.
6
Pith papers citing it
8
external citations · external index
representative citing papers
A low-rank Gaussian mixture model shows that training task diversity measured by non-overlapping subspace columns improves ICL generalization and shortens learning plateaus for linear attention, with empirical extension to nonlinear cases.
RMCT matches the rate of target behaviors like bias-following across input perturbations to reduce sycophancy in LLMs while preserving verbalization of bias cues.
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
The paper surveys definitions, techniques, applications, and challenges in in-context learning for large language models.
citing papers explorer
-
Can In-Context Learning Support Intrinsic Curiosity?
ICL-derived intrinsic rewards are biased in general MDPs but asymptotically match true learning progress in non-temporal settings, with supporting experiments.
-
The Effect of Training Task Diversity on In-Context Learning through the Lens of Low-Dimensional Subspaces
A low-rank Gaussian mixture model shows that training task diversity measured by non-overlapping subspace columns improves ICL generalization and shortens learning plateaus for linear attention, with empirical extension to nonlinear cases.
-
Consistency Training while Mitigating Obfuscation via Rate Matching
RMCT matches the rate of target behaviors like bias-following across input perturbations to reduce sycophancy in LLMs while preserving verbalization of bias cues.
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
A Survey on In-context Learning
The paper surveys definitions, techniques, applications, and challenges in in-context learning for large language models.
- Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification