A new expert-audited dataset and benchmark for ancient Chinese character exegesis shows that multimodal LLMs improve substantially when fine-tuned on domain-specific VQA data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
JieZi: A Large-Scale Expert-Audited Dataset and Benchmark for Ancient Chinese Character Exegesis
A new expert-audited dataset and benchmark for ancient Chinese character exegesis shows that multimodal LLMs improve substantially when fine-tuned on domain-specific VQA data.