Inside VLM Chart Reading: Tracing Value Reading from Vertical Bar Charts Across Space and Depth
This story is from 2026-09-15. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.13745v1 Announce Type: new Abstract: Vision--language models (VLMs) can answer chart questions accurately, but output accuracy does not show how they combine the evidence needed to recover an exact value. We study vertical-bar value reading with controlled counterfactual activation patch…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-09-15 04:00 · arXiv cs.CL
Inside VLM Chart Reading: Tracing Value Reading from Vertical Bar Charts Across Space and Depth