Unverified50% confidenceFactExact time
Existing chart evaluation benchmarks based on vision-language models (VLMs) generally lack systematic categorization of chart types and apply generic criteria to all charts.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe VLM judge uses a sample-level Visual Graph Rubric (VGR) tied to design graph elements and relations to judge aesthetic quality.72% similarUnverifiedWhen visual signals are insufficient in VLMs, language priors take over and fill in content the model did not actually see in a natural and fluent manner.71% similarUnverifiedWithout constraints, VLM judging criteria tend to drift, and sensitivity to fine-grained visual details (such as axis labels and arrow directions) is limited.69% similarUnverifiedHaving a VLM directly output pixel-level precise coordinates is using it in a way it is not good at; large models excel at semantic understanding and coarse-grained localization, but are unreliable in geometric precision.69% similarUnverifiedVLMs perform excellently on tasks such as image captioning and visual question answering, but their spatial understanding ability has long been controversial, and models may guess the answer correctly through language priors rather than truly constructing spatial representations.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079428API
curl https://kongchang.com/api/v1/knowledge/claims/1079428MCP
get_claim(id=1079428)