AnchorScore: A CLIP-Based Diagnostic of MLLM Annotation Difficulty
Multimodal large language models (MLLMs) are widely used for automated annotation, yet their per-class accuracy varies widely (e.g., 12%-98% across the 13 classes of three classroom sub-datasets) and is expensive to measure: evaluating one 27B MLLM on 5,416 validation images takes roughly 14 hours, whereas a frozen-CLIP pass over the same images completes in about 3 minutes. A low-cost signal for ranking classes by expected MLLM annotation difficulty a priori remains underexplored. Building on the AnchorProxy construct (per-class zero-shot CLIP accuracy) introduced in the companion study, this
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%Benchmarking large language models against practicing clinicians on psychopathological assessment - Nature →
- LinkedLinked via arxiv author · 85%Yan Ma →
“AnchorScore: A CLIP-Based Diagnostic of MLLM Annotation Difficulty”
- LinkedLinked via arxiv author · 85%Lizhuo Zhang →
“AnchorScore: A CLIP-Based Diagnostic of MLLM Annotation Difficulty”