ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization

• URL: http://arxiv.org/abs/2604.17512v1
• Date: Sun, 19 Apr 2026 16:05:33 GMT
• Title: ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization
• Abstract summary: ONTO is a columnar notation that declares field names once per entity and arranges values in pipe-delimited rows with indentation-based hierarchy.<n>Onto eliminates per-record key repetition while preserving human readability and nested structure support.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Serialization formats designed for document interchange impose structural overhead that becomes prohibitive when large language models consume operational data at scale. A modest dataset of 1,000 IoT sensor readings serialized as JSON requires approximately 80,000 tokens - the majority spent on repeated field names, nested braces, and structural punctuation rather than semantic content. We present ONTO (Object Notation for Token Optimization), a columnar notation that declares field names once per entity and arranges values in pipe-delimited rows with indentation-based hierarchy. This schema-once, data-many design eliminates per-record key repetition while preserving human readability and nested structure support. Evaluation across three synthetic operational datasets demonstrates 46-51% token reduction versus JSON, with stable scaling from 100 to 1,000 records. Controlled inference benchmarks on Qwen2.5-7B show corresponding 5-10% latency improvement. Comprehension validation confirms no material degradation in LLM task accuracy across lookup, counting, extraction, and aggregation operations when format context is provided. Ablation analysis reveals that key repetition accounts for the majority of JSON overhead, with indentation costs in nested structures explaining the 4-percentage-point gap between flat and hierarchical data. ONTO occupies a previously unfilled position in the serialization landscape: columnar efficiency with hierarchical structure, optimized for LLM context windows rather than document interchange. Code and specification are available at https://github.com/harsh-aranga/onto.

Related papers

• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• JTON: A Token-Efficient JSON Superset with Zen Grid Tabular Encoding for Large Language Models [0.010480658740597679]
  Zen Grid factors column headers into a single row and encodes values with domains.<n>A Rust/PyO3 reference implementation adds SIMD-accelerated syntactic parsing at 1.4x the speed of Python's.<n>Generation tests on 12 LLMs yield 100% validity in both few-shot and zero-shot settings.
  arXiv  Detail & Related papers  (2026-04-07T13:26:23Z)
• MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG [0.0]
  RAG pipelines typically rely on fixed-size chunking, which ignores document structure, fragments semantic units across boundaries, and requires multiple LLM calls per chunk for metadata extraction.<n>We present MDKeyChunker, a three-stage pipeline for Markdown documents that performs structure-aware chunking treating headers, code blocks, tables, and lists as atomic units.<n>The single-call design extracts all seven metadata fields in one LLM invocation, eliminating the need for separate per-field extraction passes.<n>Rolling key propagation replaces hand-tuned scoring with LLM-native semantic matching.
  arXiv  Detail & Related papers  (2026-03-08T07:28:53Z)
• Stacked from One: Multi-Scale Self-Injection for Context Window Extension [69.24689919827817]
  modelname is a novel framework based on multi-grained context compression and query-aware information acquisition.<n>modelnameachieves performance superior or comparable to strong baselines.
  arXiv  Detail & Related papers  (2026-03-05T03:16:16Z)
• CAE: Character-Level Autoencoder for Non-Semantic Relational Data Grouping [0.9595254895337946]
  This paper introduces a novel Character-Level Autoencoder (CAE) approach that automatically identifies and groups semantically identical columns in non-semantic relational datasets.<n>Unlike conventional Natural Language Processing (NLP) models that struggle with limitations in semantic interpretability, our approach operates at the character level with fixed dictionary constraints.<n>By maintaining a fixed dictionary size, our method significantly reduces both memory requirements and training time, enabling efficient processing of large-scale industrial data environments.
  arXiv  Detail & Related papers  (2025-11-10T22:07:22Z)
• JSON Whisperer: Efficient JSON Editing with LLMs [1.0535472555708638]
  Large language models (LLMs) can modify documents through natural language commands, but current approaches regenerate entire structures for each edit, resulting in computational inefficiency.<n>We present Whisperer, a framework that enables LLMs to generate RFC 6902 diff patches-expressing only the necessary modifications-rather than complete documents.
  arXiv  Detail & Related papers  (2025-10-06T11:36:46Z)
• DeepJSONEval: Benchmarking Complex Nested JSON Data Mining for Large Language Models [6.653834890554154]
  Multi-layer nested structures organize data into key-value pairs, arrays, and nested objects.<n>For instance, in news aggregation, a object can nest an article's metadata (title, author, date), content (text, multimedia), and multimedia information (multimedia, caption) hierarchically.<n>We introduce DeepJSONEval, a novel benchmark featuring 2100 multi-domain instances with deep nested structures, categorized by difficulty.
  arXiv  Detail & Related papers  (2025-09-30T08:18:20Z)
• SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding [55.48936731641802]
  We present the SRFUND, a hierarchically structured multi-task form understanding benchmark. SRFUND provides refined annotations on top of the original FUNSD and XFUND datasets. The dataset includes eight languages including English, Chinese, Japanese, German, French, Spanish, Italian, and Portuguese.
  arXiv  Detail & Related papers  (2024-06-13T02:35:55Z)
• Improving Text-to-SQL Semantic Parsing with Fine-grained Query Understanding [84.04706075621013]
  We present a general-purpose, modular neural semantic parsing framework based on token-level fine-grained query understanding. Our framework consists of three modules: named entity recognizer (NER), neural entity linker (NEL) and neural entity linker (NSP)
  arXiv  Detail & Related papers  (2022-09-28T21:00:30Z)
• Text Summarization with Oracle Expectation [88.39032981994535]
  Extractive summarization produces summaries by identifying and concatenating the most important sentences in a document. Most summarization datasets do not come with gold labels indicating whether document sentences are summary-worthy. We propose a simple yet effective labeling algorithm that creates soft, expectation-based sentence labels.
  arXiv  Detail & Related papers  (2022-09-26T14:10:08Z)
• Long Document Summarization with Top-down and Bottom-up Inference [113.29319668246407]
  We propose a principled inference framework to improve summarization models on two aspects. Our framework assumes a hierarchical latent structure of a document where the top-level captures the long range dependency. We demonstrate the effectiveness of the proposed framework on a diverse set of summarization datasets.
  arXiv  Detail & Related papers  (2022-03-15T01:24:51Z)
• Autoregressive Entity Retrieval [55.38027440347138]
  Entities are at the center of how we represent and aggregate knowledge. The ability to retrieve such entities given a query is fundamental for knowledge-intensive tasks such as entity linking and open-domain question answering. We propose GENRE, the first system that retrieves entities by generating their unique names, left to right, token-by-token in an autoregressive fashion.
  arXiv  Detail & Related papers  (2020-10-02T10:13:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.