SampoNLP: A Self-Referential Toolkit for Morphological Analysis of Subword Tokenizers

Documenti analoghi

• Qtok: A Comprehensive Framework for Evaluating Multilingual Tokenizer Quality in Large Language Models
  di: Chelombitko, Iaroslav, et al.
  Pubblicazione: (2024)
• Subword-Based Comparative Linguistics across 242 Languages Using Wikipedia Glottosets
  di: Chelombitko, Iaroslav, et al.
  Pubblicazione: (2026)
• Compressed code: the hidden effects of quantization and distillation on programming tokens
  di: Siniaev, Viacheslav, et al.
  Pubblicazione: (2026)
• What Matters in LLM-Based Feature Extractor for Recommender? A Systematic Analysis of Prompts, Models, and Adaptation
  di: Shi, Kainan, et al.
  Pubblicazione: (2025)
• IndiaFinBench: An Evaluation Benchmark for Large Language Model Performance on Indian Financial Regulatory Text
  di: Pall, Rajveer Singh
  Pubblicazione: (2026)