# Policy-based Sentence Simplification: Replacing Parallel Corpora with LLM-as-a-Judge

arXiv: https://arxiv.org/abs/2512.06228 · HTML: https://mlsanity.com/paper/2512.06228/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 58 references that are in the map.
- First posted on arXiv 6 Dec 2025.

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4](https://mlsanity.com/paper/2310.13988/) (2023)
- [Sentence Simplification with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.10931/) (2017)
- [ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations](https://mlsanity.com/paper/2005.00481/) (2020)
- [On Learning to Summarize with Large Language Models as References](https://mlsanity.com/paper/2305.14239/) (2023)
- [BLEU is Not Suitable for the Evaluation of Text Simplification](https://mlsanity.com/paper/1810.05995/) (2018)
- [Controllable Sentence Simplification](https://mlsanity.com/paper/1910.02677/) (2019)
- [CoEdIT: Text Editing by Task-Specific Instruction Tuning](https://mlsanity.com/paper/2305.09857/) (2023)
- [LENS: A Learnable Evaluation Metric for Text Simplification](https://mlsanity.com/paper/2212.09739/) (2022)
- [EASSE: Easier Automatic Sentence Simplification Evaluation](https://mlsanity.com/paper/1908.04567/) (2019)
- [X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale](https://mlsanity.com/paper/2410.03115/) (2024)
- [BLESS: Benchmarking Large Language Models on Sentence Simplification](https://mlsanity.com/paper/2310.15773/) (2023)
- [JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking](https://mlsanity.com/paper/2411.00142/) (2024)
- [Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA](https://mlsanity.com/paper/2305.14458/) (2023)
- [Analysing Zero-Shot Readability-Controlled Sentence Simplification](https://mlsanity.com/paper/2409.20246/) (2024)
- [Unbalanced Optimal Transport for Unbalanced Word Alignment](https://mlsanity.com/paper/2306.04116/) (2023)
- [An In-depth Evaluation of Large Language Models in Sentence Simplification with Error-based Human Assessment](https://mlsanity.com/paper/2403.04963/) (2024)
- [Evaluation Under Imperfect Benchmarks and Ratings: A Case Study in Text Simplification](https://mlsanity.com/paper/2504.09394/) (2025)
- [REFeREE: A REference-FREE Model-Based Metric for Text Simplification](https://mlsanity.com/paper/2403.17640/) (2024)
- [Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisition](https://mlsanity.com/paper/2502.11457/) (2025)

## Built on by (most cited first, 1 of 1)

- [Reasoning Model Is Superior LLM-Judge, Yet Suffers from Biases](https://mlsanity.com/paper/2601.03630/) (2026)

## Abstract (arXiv)

Sentence simplification aims to modify a sentence to make it easier to read and understand while preserving the meaning. Different applications require distinct simplification policies, such as replacing only complex words at the lexical level or rewriting the entire sentence while trading off details for simplicity. However, achieving such policy-driven control remains an open challenge. In this work, we introduce a simple yet powerful approach that leverages Large Language Model-as-a-Judge (LLM-as-a-Judge) to automatically construct policy-aligned training data, completely removing the need for costly human annotation or parallel corpora. Our method enables building simplification systems that adapt to diverse simplification policies. Remarkably, even small-scale open-source LLMs such as Phi-3-mini-3.8B surpass GPT-4o on lexical-oriented simplification, while achieving comparable performance on overall rewriting, as verified by both automatic metrics and human evaluations. The consistent improvements across model families and sizes demonstrate the robustness of our approach.