# Fine-grained Controllable Text Generation through In-context Learning with Feedback

arXiv: https://arxiv.org/abs/2406.11338 · HTML: https://mlsanity.com/paper/2406.11338/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Builds on (most cited first, 5 of 5)

- [Sentence Simplification with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.10931/) (2017)
- [Controllable Sentence Simplification](https://mlsanity.com/paper/1910.02677/) (2019)
- [Evaluating Large Language Models on Controlled Generation Tasks](https://mlsanity.com/paper/2310.14542/) (2023)
- [Controlling Pre-trained Language Models for Grade-Specific Text Simplification](https://mlsanity.com/paper/2305.14993/) (2023)
- [Controllable Text Generation in the Instruction-Tuning Era](https://mlsanity.com/paper/2405.01490/) (2024)

## Built on by (most cited first, 2 of 2)

- [LLMs syntactically adapt their language use to their conversational partner](https://mlsanity.com/paper/2503.07457/) (2025)
- [ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks](https://mlsanity.com/paper/2507.01321/) (2025)

## Abstract (arXiv)

We present a method for rewriting an input sentence to match specific values of nontrivial linguistic features, such as dependency depth. In contrast to earlier work, our method uses in-context learning rather than finetuning, making it applicable in use cases where data is sparse. We show that our model performs accurate rewrites and matches the state of the art on rewriting sentences to a specified school grade level.