Standard circuit discovery methods produce dataset-specific circuits rather than task-general ones, and a new clustering-based method discovers multiple more faithful circuits per dataset.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
years
2026 5verdicts
UNVERDICTED 5representative citing papers
POISE trains a lightweight probe on the actor's internal states to predict expected rewards for RLVR, matching DAPO performance on math benchmarks with lower compute by avoiding extra rollouts or critic models.
Gradient-informed placement of LoRA parameters recovers full performance under GRPO while random placement does not, due to differences in gradient rank and stability across training regimes.
LLMs exhibit three geometric phases in next-token prediction—seeding multiplexing, hoisting overriding, and focal convergence—where predictive subspaces rise, stabilize, and converge across layers.
RET learns temporally consistent macrovariables from LLM activations via self-supervised learning to support interpretability, early behavioral prediction, and causal intervention.
citing papers explorer
-
Data-driven Circuit Discovery for Interpretability of Language Models
Standard circuit discovery methods produce dataset-specific circuits rather than task-general ones, and a new clustering-based method discovers multiple more faithful circuits per dataset.
-
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
POISE trains a lightweight probe on the actor's internal states to predict expected rewards for RLVR, matching DAPO performance on math benchmarks with lower compute by avoiding extra rollouts or critic models.
-
Not How Many, But Which: Parameter Placement in Low-Rank Adaptation
Gradient-informed placement of LoRA parameters recovers full performance under GRPO while random placement does not, due to differences in gradient rank and stability across training regimes.
-
A Geometric Perspective on Next-Token Prediction in Large Language Models: Three Emerging Phases
LLMs exhibit three geometric phases in next-token prediction—seeding multiplexing, hoisting overriding, and focal convergence—where predictive subspaces rise, stabilize, and converge across layers.
-
Towards Effective Theory of LLMs: A Representation Learning Approach
RET learns temporally consistent macrovariables from LLM activations via self-supervised learning to support interpretability, early behavioral prediction, and causal intervention.