To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing

• URL: http://arxiv.org/abs/2604.27296v1
• Date: Thu, 30 Apr 2026 01:14:13 GMT
• Title: To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing
• Abstract summary: BlockDiff and FuncDiff are structure-aware diff formats that represent changes as block-level rewrites of syntactically coherent units.<n>AdaEdit is a general adaptive edit strategy that trains LLMs to dynamically choose the most token-efficient format between a given diff format and full code.
• Score: 54.399335188667045
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are increasingly used for code editing, yet the prevalent full-code generation paradigm suffers from severe efficiency bottlenecks, posing challenges for interactive coding assistants that demand low latency and cost. Despite the predominant focus on scaling model capabilities, the edit format itself has been largely overlooked in model training. In this paper, we begin with a systematic study of conventional diff formats and reveal that fragile offsets and fragmented hunks make generation highly unnatural for LLMs. To address it, we introduce BlockDiff and FuncDiff, two structure-aware diff formats that represent changes as block-level rewrites of syntactically coherent units such as control structures and functions. Furthermore, we propose AdaEdit, a general adaptive edit strategy that trains LLMs to dynamically choose the most token-efficient format between a given diff format and full code. Extensive experiments demonstrate that AdaEdit paired with structure-aware diff formats consistently matches the accuracy of full-code generation, while reducing both latency and cost by over 30% on long-code editing tasks.

Related papers

• Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models [0.0]
  We train two code models in two output regimes: direct generation and diff-based generation.<n>Direct generation substantially outperforms diff-based generation on every metric we measure.<n>We identify a single, architecture-independent mechanism behind the conditions where diff-based generation does win.
  arXiv  Detail & Related papers  (2026-09-05T00:13:49Z)
• FMBench: Adaptive Large Language Model Output Formatting [49.52930069696333]
  We present FMBench, a benchmark for adaptive Markdown output formatting.<n>Experiments on two model families show that SFT consistently improves semantic alignment.<n>Results also reveal an inherent trade-off between semantic and structural objectives.
  arXiv  Detail & Related papers  (2026-02-06T04:42:06Z)
• Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs [57.69190972274813]
  Diffusion Large Language Models (DLLMs) have emerged as a compelling alternative to Autoregressive models.<n>ExistingDLLMs are plagued by a severe quality-speed trade-off, where faster parallel decoding leads to significant performance degradation.<n>We introduce Wide-In, Narrow-Out (WINO), a training-free decoding algorithm that enables revokable decoding inDLLMs.
  arXiv  Detail & Related papers  (2025-07-24T16:51:33Z)
• EfficientEdit: Accelerating Code Editing via Edit-Oriented Speculative Decoding [12.558682788313371]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code editing, substantially enhancing software development productivity.<n>We propose EfficientEdit, a novel method that improves LLM-based code editing efficiency through two key mechanisms based on speculative decoding.<n> Experimental results show that EfficientEdit can achieve up to 10.38$times$ and 13.09$times$ speedup compared to standard autoregressive decoding.
  arXiv  Detail & Related papers  (2025-06-03T12:01:20Z)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)
• InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing [86.17245523439514]
  In-context learning is a promising editing method by comprehending edit information through context encoding.<n>This method is constrained by the limited context window of large language models.<n>We propose InComeS, a flexible framework that enhances LLMs' ability to process editing contexts.
  arXiv  Detail & Related papers  (2025-05-28T09:20:18Z)
• Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation [18.835969818281125]
  Large Language Models (LLMs) are increasingly required to generate text that is both factually accurate and diverse across various open-ended applications.<n>We introduce Dynamic Focus Decoding (DFD), a novel plug-and-play approach that resolves this trade-off without requiring additional data, knowledge, or models.<n>DFD adaptively adjusts the decoding focus based on distributional differences across layers, leveraging the modular and hierarchical nature of factual knowledge within LLMs.
  arXiv  Detail & Related papers  (2025-03-11T05:27:28Z)
• SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration [10.970637831760136]
  Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality.<n>We introduce SWIFT, an on-the-fly self-speculative decoding algorithm that adaptively selects intermediate layers of LLMs to skip during inference.<n>Our experiments demonstrate that SWIFT can achieve over a 1.3x-1.6x speedup while preserving the original distribution of the generated text.
  arXiv  Detail & Related papers  (2024-10-09T14:15:30Z)
• 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)

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.