InBoL improves MLLM trustworthiness by training models to refuse questions that lie beyond their extrinsic (visual) or intrinsic (knowledge) information boundaries, using confidence-aware DPO.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal
InBoL improves MLLM trustworthiness by training models to refuse questions that lie beyond their extrinsic (visual) or intrinsic (knowledge) information boundaries, using confidence-aware DPO.