TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift.
International Conference on Machine Learning , pages=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
Self-attention acts as a covariance readout that unifies in-context learning via population gradient descent and repetitive generation via asymptotic Markov behavior.
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
citing papers explorer
-
TILT: Target-induced loss tilting under covariate shift
TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift.
-
Self-Attention as a Covariance Readout: A Unified View of In-Context Learning and Repetition
Self-attention acts as a covariance readout that unifies in-context learning via population gradient descent and repetitive generation via asymptotic Markov behavior.
-
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
-
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
-
Understanding the Mechanism of Altruism in Large Language Models
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
- When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
- Many-Shot CoT-ICL: Making In-Context Learning Truly Learn