Trust the Model: Compact VLMs as In-Context Judges for Image-Text Data Quality

Documenti analoghi

• Cross-Lingual SynthDocs: A Large-Scale Synthetic Corpus for Any to Arabic OCR and Document Understanding
  di: Al-Homoud, Haneen, et al.
  Pubblicazione: (2025)
• A-SEA3L-QA: A Fully Automated Self-Evolving, Adversarial Workflow for Arabic Long-Context Question-Answer Generation
  di: Wang, Kesen, et al.
  Pubblicazione: (2025)
• Multi-Agent Interactive Question Generation Framework for Long Document Understanding
  di: Wang, Kesen, et al.
  Pubblicazione: (2025)
• FairJudge: Abstention-Aware Multimodal Judges for Fairness and Alignment Evaluation in Text-to-Image Models
  di: Sahili, Zahraa Al, et al.
  Pubblicazione: (2025)
• Bias in the Picture: Benchmarking VLMs with Social-Cue News Images and LLM-as-Judge Assessment
  di: Narayanan, Aravind, et al.
  Pubblicazione: (2025)