LTS-FS locates hallucination-relevant layers in LVLMs via causal attribution on a constructed dataset and applies sparse layerwise feature steering to mitigate hallucinations while preserving general task performance.
Since existing fea- ture steering techniques have not been evaluated on larger 70B-scale models, extending our method to 70B models re- mains a challenge
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
LTS-FS locates hallucination-relevant layers in LVLMs via causal attribution on a constructed dataset and applies sparse layerwise feature steering to mitigate hallucinations while preserving general task performance.