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.
arXiv preprint arXiv:2405.09719 (2024)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
SSAG bypasses logit suppression in five LLMs to produce harmful responses at 95% success rate and 86% lower latency; VulMine reaches 77% attack success against defenses.
Training-free methods for LLM trustworthiness show inconsistent results across dimensions, with clear trade-offs in utility, robustness, and overhead depending on where they intervene during inference.
citing papers explorer
-
Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning
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.
-
Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
SSAG bypasses logit suppression in five LLMs to produce harmful responses at 95% success rate and 86% lower latency; VulMine reaches 77% attack success against defenses.
-
A Systematic Study of Training-Free Methods for Trustworthy Large Language Models
Training-free methods for LLM trustworthiness show inconsistent results across dimensions, with clear trade-offs in utility, robustness, and overhead depending on where they intervene during inference.