mlsanityData to 14 Oct 2026

CLEAR: A Comprehensive Linguistic Evaluation of Argument Rewriting by Large Language Models

arXiv 2509.15027 ↗First posted 18 Sep 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

While LLMs have been extensively studied on general text generation tasks, there is less research on text rewriting, a task related to general text generation, and particularly on the behavior of models on this task. In this paper we analyze what changes LLMs make in a text rewriting setting. We focus specifically on argumentative texts and their improvement, a task named Argument Improvement (ArgImp). We present CLEAR: an evaluation pipeline consisting of 57 metrics mapped to four linguistic levels: lexical, syntactic, semantic and pragmatic. This pipeline is used to examine the qualities of LLM-rewritten arguments on a broad set of argumentation corpora and compare the behavior of different LLMs on this task and analyze the behavior of different LLMs on this task in terms of linguistic levels. By taking all four linguistic levels into consideration, we find that the models perform ArgImp by shortening the texts while simultaneously increasing average word length and merging sentences. Overall we note an increase in the persuasion and coherence dimensions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 71 references that are in the map. First posted on arXiv 18 Sep 2025.

Builds on

30 of 71 references.

References · 30

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  4. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,184
  5. 2024OLMo: Accelerating the Science of Language Modelscited by 613
  6. 2024Humans or LLMs as the Judge? A Study on Judgement Biasescited by 323
  7. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 250
  8. 2017Style Transfer in Text: Exploration and Evaluationcited by 146
  9. 2024HelpSteer2-Preference: Complementing Ratings with Preferencescited by 130
  10. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structurescited by 110
  11. 2023Branch-Solve-Merge Improves Large Language Model Evaluation and Generationcited by 106
  12. 2016Parsing Argumentation Structures in Persuasive Essayscited by 101
18 more
  1. 2020ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformationscited by 101
  2. 2023RewriteLM: An Instruction-Tuned Large Language Model for Text Rewritingcited by 67
  3. 2017Paraphrase Generation with Deep Reinforcement Learningcited by 58
  4. 2024Revisiting Demonstration Selection Strategies in In-Context Learningcited by 58
  5. 2023Exploring the Potential of Large Language Models in Computational Argumentationcited by 42
  6. 2020TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restylingcited by 40
  7. 2020GRUEN for Evaluating Linguistic Quality of Generated Textcited by 37
  8. 2024Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generationcited by 29
  9. 2021Many Hands Make Light Work: Using Essay Traits to Automatically Score Essayscited by 25
  10. 2023Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoringcited by 24
  11. 2024Are Large Language Models Reliable Argument Quality Annotators?cited by 24
  12. 2024Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practicescited by 20
  13. 2023Large Language Model (LLM) Bias Index -- LLMBIcited by 14
  14. 2023AMERICANO: Argument Generation with Discourse-driven Decomposition and Agent Interactioncited by 8
  15. 2020A Corpus for Argumentative Writing Support in Germancited by 7
  16. 2024"Let's Argue Both Sides": Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilitiescited by 4
  17. 2024Assessing Open-Source Large Language Models on Argumentation Mining Subtaskscited by 3
  18. 2024Chain-of-MetaWriting: Linguistic and Textual Analysis of How Small Language Models Write Young Students Textscited by 2

Built on by

Not cited yet.