Not All Tokens Matter: Data-Centric Optimization for Efficient Code Summarization
A new preprint investigates token-level reduction techniques to lower computational costs in large language model (LLM)-based code summarization. The study finds that optimal token reduction strategies are highly language-dependent: AST-based reduction improves Java summarization performance by 37% but degrades Python by up to 49%, while CrystalBLEU-guided pruning achieves robust cross-language token reduction of 60-72%. Function signature-based reduction is optimal for Python, achieving 83% token reduction while maintaining summary quality.
Why it matters: The work demonstrates that language-aware token curation is crucial for efficient code summarization, challenging assumptions about the transferability of token reduction strategies across programming languages.
Full story at: arXiv Software Engineering ↗