S³E framework finds excess decision-state displacement under semantic stress in multimodal models despite consistent correct forced-choice behavior.
arXiv preprint arXiv:2410.03659 (2024) A Judge Reliability and Probe Detection Hall
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
ChronoPhyBench is a new benchmark and dataset for chronological physical dynamics reasoning that combines video-conditioned next-state prediction with VQA to reduce language bias in MLLM evaluation.
MLLMs show late-layer textual override of correct visual predictions, with a directional signature enabling a simple inference-time recovery method that improves conflict benchmarks by up to 9.4%.
RIHA proposes a hierarchical alignment transformer that uses multi-scale visual and textual feature pyramids plus optimal transport to generate more accurate radiology reports from medical images.
Causal path-patching analysis across five MLLMs identifies distributed hallucination-driving attention heads and localized resisting heads whose imbalance biases generation toward erroneous text over visual evidence; a conditional intervention MACI suppresses the driving heads and cuts hallucination
citing papers explorer
-
When Correct Decisions Hide Internal Stress: Decision-State Probing in Multimodal Language Models
S³E framework finds excess decision-state displacement under semantic stress in multimodal models despite consistent correct forced-choice behavior.
-
ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?
ChronoPhyBench is a new benchmark and dataset for chronological physical dynamics reasoning that combines video-conditioned next-state prediction with VQA to reduce language bias in MLLM evaluation.
-
MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias
MLLMs show late-layer textual override of correct visual predictions, with a directional signature enabling a simple inference-time recovery method that improves conflict benchmarks by up to 9.4%.
-
RIHA: Report-Image Hierarchical Alignment for Radiology Report Generation
RIHA proposes a hierarchical alignment transformer that uses multi-scale visual and textual feature pyramids plus optimal transport to generate more accurate radiology reports from medical images.
-
Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination
Causal path-patching analysis across five MLLMs identifies distributed hallucination-driving attention heads and localized resisting heads whose imbalance biases generation toward erroneous text over visual evidence; a conditional intervention MACI suppresses the driving heads and cuts hallucination