When reflections localize early errors, in-context search solves exp-small pass-rate problems with poly sequential attempts; otherwise it offers no asymptotic gain over parallel sampling, and the update is learnable and RLVR-optimal.
International Conference on Machine Learning , pages=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8roles
background 1polarities
background 1representative citing papers
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 acts as a covariance readout that unifies in-context learning via population gradient descent and repetitive generation via asymptotic Markov behavior.
The paper proposes Strategic Prior-data Fitted Network (SPN), an inference-time framework that adapts pretrained tabular foundation models (PFNs) to strategic manipulation by aligning predictions with approximated post-manipulation distributions via strategic in-context examples.
Many-shot CoT-ICL improves when demonstrations are ordered for smooth conceptual progression, with CDS delivering up to 5.42 percentage-point gains on math tasks using 64 examples.
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
-
When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning
When reflections localize early errors, in-context search solves exp-small pass-rate problems with poly sequential attempts; otherwise it offers no asymptotic gain over parallel sampling, and the update is learnable and RLVR-optimal.
-
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.
-
When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
The paper proposes Strategic Prior-data Fitted Network (SPN), an inference-time framework that adapts pretrained tabular foundation models (PFNs) to strategic manipulation by aligning predictions with approximated post-manipulation distributions via strategic in-context examples.
-
Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
Many-shot CoT-ICL improves when demonstrations are ordered for smooth conceptual progression, with CDS delivering up to 5.42 percentage-point gains on math tasks using 64 examples.
-
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.