# HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks

arXiv: https://arxiv.org/abs/2512.12544 · HTML: https://mlsanity.com/paper/2512.12544/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 14 Dec 2025.

## Builds on (most cited first, 30 of 31)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [FineSurE: Fine-grained Summarization Evaluation using LLMs](https://mlsanity.com/paper/2407.00908/) (2024)
- [CoEdIT: Text Editing by Task-Specific Instruction Tuning](https://mlsanity.com/paper/2305.09857/) (2023)
- [RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting](https://mlsanity.com/paper/2305.15685/) (2023)
- [Are Your LLMs Capable of Stable Reasoning?](https://mlsanity.com/paper/2412.13147/) (2024)
- [Seq2Edits: Sequence Transduction Using Span-level Edit Operations](https://mlsanity.com/paper/2009.11136/) (2020)
- [Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions](https://mlsanity.com/paper/2312.12450/) (2023)
- [Beyond the Chat: Executable and Verifiable Text-Editing with LLMs](https://mlsanity.com/paper/2309.15337/) (2023)
- [BALF: Simple and Efficient Blur Aware Local Feature Detector](https://mlsanity.com/paper/2211.14731/) (2022)
- [Beemo: Benchmark of Expert-edited Machine-generated Outputs](https://mlsanity.com/paper/2411.04032/) (2024)
- [Improving Attributed Text Generation of Large Language Models via Preference Learning](https://mlsanity.com/paper/2403.18381/) (2024)
- [Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications](https://mlsanity.com/paper/2502.13358/) (2025)
- [Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch](https://mlsanity.com/paper/2403.14729/) (2024)
- [PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization](https://mlsanity.com/paper/2509.12446/) (2025)
- [Exploring the Capabilities of LLMs for Code Change Related Tasks](https://mlsanity.com/paper/2407.02824/) (2024)
- [SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation](https://mlsanity.com/paper/2412.05818/) (2024)
- [Fact-based Text Editing](https://mlsanity.com/paper/2007.00916/) (2020)
- [Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review](https://mlsanity.com/paper/2410.03663/) (2024)
- [mEdIT: Multilingual Text Editing via Instruction Tuning](https://mlsanity.com/paper/2402.16472/) (2024)
- [ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning](https://mlsanity.com/paper/2501.15316/) (2025)
- [Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics](https://mlsanity.com/paper/2408.02672/) (2024)
- [Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study](https://mlsanity.com/paper/2503.00985/) (2025)
- [Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps](https://mlsanity.com/paper/2407.05165/) (2024)
- [XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates](https://mlsanity.com/paper/2309.11063/) (2023)
- [DocMEdit: Towards Document-Level Model Editing](https://mlsanity.com/paper/2505.19572/) (2025)

## Built on by (most cited first, 4 of 4)

- [HyperFL: Query-Adaptive Representation Learning for Software Fault Localization](https://mlsanity.com/paper/2608.02967/) (2026)
- [Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models](https://mlsanity.com/paper/2608.09109/) (2026)
- [Can LLMs Separate Pasted Artifacts from User Speech? Absorption at Unmarked Prompt Seams](https://mlsanity.com/paper/2610.04210/) (2026)
- [WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs](https://mlsanity.com/paper/2610.17355/) (2026)

## Abstract (arXiv)

Instruction-based text editing is increasingly critical for real-world applications such as code editors (e.g., Cursor), but Large Language Models (LLMs) continue to struggle with this task. Unlike free-form generation, editing requires faithfully implementing user instructions while preserving unchanged content, as even minor unintended modifications can break functionality. Existing approaches treat editing as generic text generation, leading to two key failures: they struggle to faithfully align edits with diverse user intents, and they often over-edit unchanged regions. We propose HyperEdit to address both issues. First, we introduce hypernetwork-based dynamic adaptation that generates request-specific parameters, enabling the model to tailor its editing strategy to each instruction. Second, we develop difference-aware regularization that focuses supervision on modified spans, preventing over-editing while ensuring precise, minimal changes. HyperEdit achieves a 9%--30% relative improvement in BLEU on modified regions over state-of-the-art baselines, despite utilizing only 3B parameters.