JTON: A Token-Efficient JSON Superset with Zen Grid Tabular Encoding for Large Language Models
This addresses the problem of high token costs and context waste for developers and researchers using LLMs with structured data, though it is an incremental improvement over existing JSON serialization methods.
The paper tackles the token inefficiency of JSON for tabular data in LLMs by introducing JTON with Zen Grid encoding, which reduces token counts by 15-60% (28.5% average) and maintains or slightly improves LLM comprehension accuracy while ensuring 100% syntactic validity in generation tests.
When LLMs process structured data, the serialization format directly affects cost and context utilization. Standard JSON wastes tokens repeating key names in every row of a tabular array--overhead that scales linearly with row count. This paper presents JTON (JSON Tabular Object Notation), a strict JSON superset whose main idea, Zen Grid, factors column headers into a single row and encodes values with semicolons, preserving JSON's type system while cutting redundancy. Across seven real-world domains, Zen Grid reduces token counts by 15-60% versus JSON compact (28.5% average; 32% with bare_strings). Comprehension tests on 10 LLMs show a net +0.3 pp accuracy gain over JSON: four models improve, three hold steady, and three dip slightly. Generation tests on 12 LLMs yield 100% syntactic validity in both few-shot and zero-shot settings. A Rust/PyO3 reference implementation adds SIMD-accelerated parsing at 1.4x the speed of Python's json module. Code, a 683-vector test suite, and all experimental data are publicly available.