Saved in:
Bibliographic Details
Main Authors: Forrester, Chris, Sulea, Octavia
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.08058
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915287739138048
author Forrester, Chris
Sulea, Octavia
author_facet Forrester, Chris
Sulea, Octavia
contents Compute optimization using token reduction of LLM prompts is an emerging task in the fields of NLP and next generation, agentic AI. In this white paper, we introduce a novel (patent pending) text representation scheme and a first-of-its-kind word-level semantic compression of paragraphs that can lead to over 90% token reduction, while retaining high semantic similarity to the source text. We explain how this novel compression technique can be lossless and how the detail granularity is controllable. We discuss benchmark results over open source data (i.e. Bram Stoker's Dracula available through Project Gutenberg) and show how our results hold at the paragraph level, across multiple genres and models.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08058
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method
Forrester, Chris
Sulea, Octavia
Computation and Language
Compute optimization using token reduction of LLM prompts is an emerging task in the fields of NLP and next generation, agentic AI. In this white paper, we introduce a novel (patent pending) text representation scheme and a first-of-its-kind word-level semantic compression of paragraphs that can lead to over 90% token reduction, while retaining high semantic similarity to the source text. We explain how this novel compression technique can be lossless and how the detail granularity is controllable. We discuss benchmark results over open source data (i.e. Bram Stoker's Dracula available through Project Gutenberg) and show how our results hold at the paragraph level, across multiple genres and models.
title Hypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method
topic Computation and Language
url https://arxiv.org/abs/2505.08058