Extend evaluation to full fine-tuning and additional document genres

Extend the evaluation of conditioned cross-granularity training beyond LoRA fine-tuning and the studied receipt and scanned-business-form genres, including full fine-tuning and further document genres.

Background

The empirical study evaluates Qwen3-VL models at two scales using LoRA fine-tuning and three document corpora: two receipt datasets and one scanned business-form dataset. The authors explicitly identify full-parameter fine-tuning and additional document genres as unresolved extensions, which would test whether the reported reinforcement and collapse-avoidance effects generalize beyond the present training regime and domains.

References

Complete-candidate likelihood, broader prompt-selection budgets, and training-objective controls remain open.

— From Text Decisions to Pixels: An Study of Jev-Style Visual Choice Model  (2609.29283 - Zhou et al., 24 Sep 2026) in Appendix, Section Staged Research Milestones, Stage 1: extend the matched interface comparison

Our evidence covers two receipt corpora and one corpus of scanned business forms, one VLM family at two scales and LoRA fine-tuning; full fine-tuning and further genres are left open, and the FUNSD corpus has $149$ training and $50$ test documents, so its intervals are correspondingly wide, with three seeds run only for mixed, conditioned and the neutral control.

— Joint Training Is Not Enough: Conditioned Cross-Granularity Training for Multimodal Document Understanding  (2609.00756 - Gan et al., 1 Sep 2026) in Limitations section