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.
and Potts, Christopher , year =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
AI deployment in high-stakes areas requires domain-scoped calibrated verification with monitoring and revocation, using a proposed six-component Verification Coverage standard instead of mechanistic interpretability.
Decoder-based VLMs hallucinate due to geometric over-alignment of visual embeddings with the text manifold in a universal dataset-agnostic subspace, mitigated by projecting out the linguistic bias.
Overthinking in medical QA is linearly decodable at 71.6% accuracy yet fixed residual-stream steering yields no correction across 29 configurations, while enabling selective abstention with AUROC 0.610.
citing papers explorer
-
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.
-
The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime
AI deployment in high-stakes areas requires domain-scoped calibrated verification with monitoring and revocation, using a proposed six-component Verification Coverage standard instead of mechanistic interpretability.
-
When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
Decoder-based VLMs hallucinate due to geometric over-alignment of visual embeddings with the text manifold in a universal dataset-agnostic subspace, mitigated by projecting out the linguistic bias.
-
Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes
Overthinking in medical QA is linearly decodable at 71.6% accuracy yet fixed residual-stream steering yields no correction across 29 configurations, while enabling selective abstention with AUROC 0.610.