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

• URL: http://arxiv.org/abs/2512.06228v1
• Date: Sat, 06 Dec 2025 00:29:49 GMT
• Title: Policy-based Sentence Simplification: Replacing Parallel Corpora with LLM-as-a-Judge
• Abstract summary: Sentence simplification aims to modify a sentence to make it easier to read and understand while preserving the meaning.<n>Different applications require distinct simplification policies, such as replacing only complex words at the lexical level or rewriting the entire sentence.<n>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.
• Score: 14.557044002544586
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL [64.4276583943816]
  Reinforcement learning for non-verifiable instruction relies on judges with prompt-specific rubrics as reward signals.<n>While recent methods adapt these rubrics to the evolving policy during training, the training prompts themselves remain static.<n>This static approach often results in a critical misalignment between prompt difficulty and policy capability, leaving the judge unable to recover a discriminative reward signal.
  arXiv  Detail & Related papers  (2026-07-05T17:05:13Z)
• Let's Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification [8.985694067999864]
  Large language models demonstrate limited capability in proficiency-controlled sentence simplification.<n>We propose a framework that decomposes complex simplifications into manageable steps.<n> Evaluation on five languages shows our approach improves simplification effectiveness while reducing computational steps by 22-42%.
  arXiv  Detail & Related papers  (2026-02-07T11:21:17Z)
• LLMs Can Generate a Better Answer by Aggregating Their Own Responses [83.69632759174405]
  Large Language Models (LLMs) have shown remarkable capabilities across tasks, yet they often require additional prompting techniques when facing complex problems.<n>We argue this limitation stems from the fact that common LLM post-training procedures lack explicit supervision for discriminative judgment tasks.<n>We propose Generative Self-Aggregation (GSA), a novel prompting method that improves answer quality without requiring the model's discriminative capabilities.
  arXiv  Detail & Related papers  (2025-03-06T05:25:43Z)
• Simple is not Enough: Document-level Text Simplification using Readability and Coherence [20.613410797137036]
  We present the SimDoc system, a simplification model considering simplicity, readability, and discourse aspects, such as coherence.<n>We include multiple objectives during training, considering simplicity, readability, and coherence altogether.<n>We present a comparative analysis in which we evaluate our proposed models in a zero-shot, few-shot, and fine-tuning setting using document-level TS corpora.
  arXiv  Detail & Related papers  (2024-12-24T19:05:21Z)
• Analysing Zero-Shot Readability-Controlled Sentence Simplification [54.09069745799918]
  We investigate how different types of contextual information affect a model's ability to generate sentences with the desired readability.<n>Results show that all tested models struggle to simplify sentences due to models' limitations and characteristics of the source sentences.<n>Our experiments also highlight the need for better automatic evaluation metrics tailored to RCTS.
  arXiv  Detail & Related papers  (2024-09-30T12:36:25Z)
• An LLM-Enhanced Adversarial Editing System for Lexical Simplification [10.519804917399744]
  Lexical Simplification aims to simplify text at the lexical level. Existing methods rely heavily on annotated data. We propose a novel LS method without parallel corpora.
  arXiv  Detail & Related papers  (2024-02-22T17:04:30Z)
• Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA [21.147261039292026]
  We introduce SALSA, an edit-based human annotation framework. We develop twenty one linguistically grounded edit types, covering the full spectrum of success and failure. We develop LENS-SALSA, a reference-free automatic simplification metric, trained to predict sentence- and word-level quality simultaneously.
  arXiv  Detail & Related papers  (2023-05-23T18:30:49Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)
• Unsupervised Sentence Simplification via Dependency Parsing [4.337513096197002]
  We propose a simple yet novel unsupervised sentence simplification system. It harnesses parsing structures together with sentence embeddings to produce linguistically effective simplifications. We establish the unsupervised state-of-the-art at 39.13 SARI on TurkCorpus set and perform competitively against supervised baselines on various quality metrics.
  arXiv  Detail & Related papers  (2022-06-10T07:55:25Z)
• Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation [75.86581380817464]
  A SimulST system generally includes two components: the pre-decision that aggregates the speech information and the policy that decides to read or write. This paper proposes to model the adaptive policy by adapting the Continuous Integrate-and-Fire (CIF) Compared with monotonic multihead attention (MMA), our method has the advantage of simpler computation, superior quality at low latency, and better generalization to long utterances.
  arXiv  Detail & Related papers  (2022-03-22T23:33:18Z)
• Controllable Text Simplification with Explicit Paraphrasing [88.02804405275785]
  Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that are trained end-to-end to perform all these operations simultaneously. We propose a novel hybrid approach that leverages linguistically-motivated rules for splitting and deletion, and couples them with a neural paraphrasing model to produce varied rewriting styles.
  arXiv  Detail & Related papers  (2020-10-21T13:44:40Z)
• ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations [97.27005783856285]
  This paper introduces ASSET, a new dataset for assessing sentence simplification in English. We show that simplifications in ASSET are better at capturing characteristics of simplicity when compared to other standard evaluation datasets for the task.
  arXiv  Detail & Related papers  (2020-05-01T16:44:54Z)

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.