# Dr Genre: Reinforcement Learning from Decoupled LLM Feedback for Generic Text Rewriting

arXiv: https://arxiv.org/abs/2503.06781 · HTML: https://mlsanity.com/paper/2503.06781/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer](https://mlsanity.com/paper/1803.06535/) (2018)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [Revisiting Self-Training for Neural Sequence Generation](https://mlsanity.com/paper/1909.13788/) (2019)
- [Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation](https://mlsanity.com/paper/2407.10817/) (2024)
- [RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting](https://mlsanity.com/paper/2305.15685/) (2023)
- [Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents](https://mlsanity.com/paper/2402.00798/) (2024)
- [Parallel Data Augmentation for Formality Style Transfer](https://mlsanity.com/paper/2005.07522/) (2020)
- [FRUIT: Faithfully Reflecting Updated Information in Text](https://mlsanity.com/paper/2112.08634/) (2021)
- [EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start](https://mlsanity.com/paper/2205.12209/) (2022)
- [Unsupervised Paraphrasing via Deep Reinforcement Learning](https://mlsanity.com/paper/2007.02244/) (2020)
- [ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs](https://mlsanity.com/paper/2402.11764/) (2024)
- [Empowering Large Language Models for Textual Data Augmentation](https://mlsanity.com/paper/2404.17642/) (2024)
- [Don't Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewriting](https://mlsanity.com/paper/2305.14755/) (2023)
- [DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting](https://mlsanity.com/paper/2101.11836/) (2021)

## Built on by (most cited first, 3 of 3)

- [LeMix: Unified Scheduling for LLM Training and Inference on Multi-GPU Systems](https://mlsanity.com/paper/2507.21276/) (2025)
- [MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignment](https://mlsanity.com/paper/2510.03283/) (2025)
- [PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning](https://mlsanity.com/paper/2605.23027/) (2026)

## Abstract (arXiv)

Generic text rewriting is a prevalent large language model (LLM) application that covers diverse real-world tasks, such as style transfer, fact correction, and email editing. These tasks vary in rewriting objectives (e.g., factual consistency vs. semantic preservation), making it challenging to develop a unified model that excels across all dimensions. Existing methods often specialize in either a single task or a specific objective, limiting their generalizability. In this work, we introduce a generic model proficient in factuality, stylistic, and conversational rewriting tasks. To simulate real-world user rewrite requests, we construct a conversational rewrite dataset, ChatRewrite, that presents ``natural''-sounding instructions, from raw emails using LLMs. Combined with other popular rewrite datasets, including LongFact for the factuality rewrite task and RewriteLM for the stylistic rewrite task, this forms a broad benchmark for training and evaluating generic rewrite models. To align with task-specific objectives, we propose Dr Genre, a Decoupled-reward learning framework for Generic rewriting, that utilizes objective-oriented reward models with a task-specific weighting. Evaluation shows that approach delivers higher-quality rewrites across all targeted tasks, improving objectives including instruction following (agreement), internal consistency (coherence), and minimal unnecessary edits (conciseness).