התכמות של פרומפטים למודלי שפה גדולים: פייפליין טבעי, לא-מלמד, עם ניתוח פארטו אמפירי בארבע עשרה קטגוריות

תקציר מקורי באנגליתarXiv:2609.13154v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have made prompts increasingly large and complex. Techniques such as chain-of-thought reasoning (Wei et al., 2022) and in-context learning (Brown et al., 2020) frequently push real-world prompts past several thousand tokens, increasing inference cost and latency. Learned compression methods such as LLMLingua (Jiang et al., 2023) and Selective Context (Li et al., 2023) achieve high compression ratios but require auxiliary language models and are non-deterministic. We ask a complementary question: how far can a training-free, fully deterministic, CPU-only pipeline based on classical lexical NLP be pushed before output quality degrades significantly? Eleven toggleable lexical transformations - stop