A blank-image ablation test reveals that high probe accuracy on VLM spatial reasoning frequently reflects priors or inverted signs rather than image grounding, with horizontal grounded, vertical prior, and depth inverted.
Patel, Parth Sheth, et al
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 3representative citing papers
Adaptive scheduling of interventions in discrete diffusion language models, timed to attribute-specific commitment schedules discovered with sparse autoencoders, delivers precise multi-attribute steering up to 93% strength while preserving generation quality.
Fine-tuning LLMs on an unseen language teaches syntax but fails to transfer semantic competence, leaving Python with up to a 19% performance advantage and no tested intervention closing the gap.
Transformer hidden states contain rank-indexed orientation signatures for true r-argument relations (r=3-6) that survive surface controls and can be patched to alter model outputs on relation tasks.
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.
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
-
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.
-
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.