JSON Whisperer: Efficient JSON Editing with LLMs

• URL: http://arxiv.org/abs/2510.04717v1
• Date: Mon, 06 Oct 2025 11:36:46 GMT
• Title: JSON Whisperer: Efficient JSON Editing with LLMs
• Authors: Sarel Duanis, Asnat Greenstein-Messica, Eliya Habba,
• Abstract summary: 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.
• Score: 1.0535472555708638
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large language models (LLMs) can modify JSON documents through natural language commands, but current approaches regenerate entire structures for each edit, resulting in computational inefficiency. We present JSON Whisperer, a framework that enables LLMs to generate RFC 6902 diff patches-expressing only the necessary modifications-rather than complete documents. We identify two key challenges in patch-based editing: (1) LLMs often miss related updates when generating isolated patches, and (2) array manipulations require tracking index shifts across operations, which LLMs handle poorly. To address these issues, we introduce EASE (Explicitly Addressed Sequence Encoding), which transforms arrays into dictionaries with stable keys, eliminating index arithmetic complexities. Our evaluation shows that patch generation with EASE reduces token usage by 31% while maintaining edit quality within 5% of full regeneration with particular gains for complex instructions and list manipulations. The dataset is available at: https://github.com/emnlp2025/JSON-Whisperer/

Related papers

• 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)
• Earley-Driven Dynamic Pruning for Efficient Structured Decoding [6.905994258490735]
  Large Language Models (LLMs) have shown remarkable capabilities, yet ensuring their outputs conform to strict structural or grammatical constraints remains challenging.<n>We propose a novel strategy based on the Earley algorithm that identifies and eliminates invalid or redundant Earley states in real-time.<n>We implement a new constrained decoding engine called Formatron which also incorporates existing optimizations.
  arXiv  Detail & Related papers  (2025-06-01T20:05:30Z)
• Learning to Generate Structured Output with Schema Reinforcement Learning [83.09230124049667]
  This study investigates the structured generation capabilities of large language models (LLMs)<n>We find that the latest LLMs are still struggling to generate a valid string.<n>Our models demonstrate significant improvement in both generating outputs and downstream tasks.
  arXiv  Detail & Related papers  (2025-02-26T06:45:29Z)
• AnyEdit: Edit Any Knowledge Encoded in Language Models [69.30638272162267]
  We propose AnyEdit, a new autoregressive editing paradigm for large language models (LLMs)<n>It decomposes long-form knowledge into sequential chunks and iteratively edits the key token in each chunk, ensuring consistent and accurate outputs.<n>It outperforms strong baselines by 21.5% on benchmarks including UnKEBench, AKEW, and our new EditEverything dataset for long-form diverse-formatted knowledge.
  arXiv  Detail & Related papers  (2025-02-08T16:18:37Z)
• Efficient Real-time Refinement of Language Model Text Generation [65.1937138219008]
  Large language models (LLMs) have shown remarkable performance across a wide range of natural language tasks.<n>A critical challenge remains in that they sometimes generate factually incorrect answers.<n>We propose Streaming-VR, a novel approach designed to enhance the efficiency of verification and refinement of LLM outputs.
  arXiv  Detail & Related papers  (2025-01-14T03:59:48Z)
• SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution [56.9361004704428]
  Large Language Models (LLMs) have demonstrated remarkable proficiency across a variety of complex tasks.<n>SWE-Fixer is a novel open-source framework designed to effectively and efficiently resolve GitHub issues.<n>We assess our approach on the SWE-Bench Lite and Verified benchmarks, achieving competitive performance among open-source models.
  arXiv  Detail & Related papers  (2025-01-09T07:54:24Z)
• IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking [5.174301428591665]
  Large Language Models (LLMs) are widely used for tasks such as natural language and code generation.<n>Their outputs often suffer from issues like hallucination, toxicity, and incorrect results.<n>Current libraries for structured LLM generation rely on left-to-right decoding without support for backtracking.<n>IterGen enables users to move both forward and backward within the generated output based on grammar symbols.
  arXiv  Detail & Related papers  (2024-10-09T16:21:38Z)
• ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA [55.697627106315004]
  Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors.<n>Previous approaches manage sequential edits by freezing original parameters and discretely allocating new parameters for each knowledge update.<n>We propose ELDER, a novel approach to create a continuous association between data and adapters.
  arXiv  Detail & Related papers  (2024-08-19T02:27:00Z)
• Robustness of LLMs to Perturbations in Text [2.0670689746336]
  Large language models (LLMs) have shown impressive performance, but can they handle the inevitable noise in real-world data? This work tackles this critical question by investigating LLMs' resilience against morphological variations in text. Our findings show that contrary to popular beliefs, generative LLMs are quiet robust to noisy perturbations in text.
  arXiv  Detail & Related papers  (2024-07-12T04:50:17Z)
• The Ups and Downs of Large Language Model Inference with Vocabulary Trimming by Language Heuristics [74.99898531299148]
  This research examines vocabulary trimming (VT) inspired by restricting embedding entries to the language of interest to bolster time and memory efficiency. We apply two languages to trim the full vocabulary - Unicode-based script filtering and corpus-based selection - to different language families and sizes. It is found that VT reduces the memory usage of small models by nearly 50% and has an upper bound of 25% improvement in generation speed.
  arXiv  Detail & Related papers  (2023-11-16T09:35:50Z)

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.