Aggregating many LLM-synthesized weak verifiers via weak learning from sparse labels yields stronger verifiers that improve F1 by up to 7X over direct LLM judges on 3D room and 2D poster tasks and boost generation quality by 66.2%.
Document Analysis and Recognition – ICDAR 2025: 19th International Conference, Wuhan, China, September 16–21
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Aggregating LLM-Based Weak Verifiers for Spatial Layout Generation
Aggregating many LLM-synthesized weak verifiers via weak learning from sparse labels yields stronger verifiers that improve F1 by up to 7X over direct LLM judges on 3D room and 2D poster tasks and boost generation quality by 66.2%.