Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs
Despite the rapid progress of Multimodal Large Language Models (MLLMs), they still suffer from untruthfulness issues, such as visual hallucinations, content fabrication, and unfaithful reasoning, which substantially undermine their faithfulness and practical utility. Alignment methods based on human preference, such as Direct Preference Optimization (DPO), have been widely adopted to address these issues. However, multimodal reasoning errors often propagate across stages, and final-answer errors can often be traced to mistakes in early grounding stages, yet standard DPO typically applies prefe
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%Identifying Interactions at Scale for LLMs →
- PossiblePossibly related (embedding) · 48%Large Tabular Models Excel Where LLMs Fail →
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- LinkedLinked via arxiv author · 85%Zhixiao Zheng →
“Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs”
- LinkedLinked via arxiv author · 85%Zheren Fu →
“Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs”
- LinkedLinked via arxiv author · 85%Zhiyuan Yao →
“Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs”
- LinkedLinked via arxiv author · 85%Chunxiao Liu →
“Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs”
- LinkedLinked via arxiv author · 85%Dongming Zhang →
“Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs”