MoVoC: Morphology-Aware Subword Construction for Geez Script Languages

Documenti analoghi

• Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency
  di: Teklehaymanot, Hailay Kidu, et al.
  Pubblicazione: (2025)
• Low-Resource English-Tigrinya MT: Leveraging Multilingual Models, Custom Tokenizers, and Clean Evaluation Benchmarks
  di: Teklehaymanot, Hailay Kidu, et al.
  Pubblicazione: (2025)
• Morphological Synthesizer for Ge'ez Language: Addressing Morphological Complexity and Resource Limitations
  di: Gebremariam, Gebrearegawi, et al.
  Pubblicazione: (2025)
• LLM-as-a-Judge: Rapid Evaluation of Legal Document Recommendation for Retrieval-Augmented Generation
  di: Pradhan, Anu, et al.
  Pubblicazione: (2025)
• What Matters in LLM-Based Feature Extractor for Recommender? A Systematic Analysis of Prompts, Models, and Adaptation
  di: Shi, Kainan, et al.
  Pubblicazione: (2025)