From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression

Documenti analoghi

• A Comprehensive Survey of Compression Algorithms for Language Models
  di: Park, Seungcheol, et al.
  Pubblicazione: (2024)
• The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts
  di: Johnson, Warren
  Pubblicazione: (2026)
• GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion
  di: Lee, Sunkyung, et al.
  Pubblicazione: (2025)
• Lossless Prompt Compression via Dictionary-Encoding and In-Context Learning: Enabling Cost-Effective LLM Analysis of Repetitive Data
  di: de Campos, Andresa Rodrigues, et al.
  Pubblicazione: (2026)
• Streamlining Redundant Layers to Compress Large Language Models
  di: Chen, Xiaodong, et al.
  Pubblicazione: (2024)