Year: 2026
Type: conference-paper
Abstract: Editing human-written text has become a standard use case of large language models (LLMs), for example, to make one's arguments more appropriate for a discussion.Comparing human to LLM-generated edits, however, we observe a mismatch in editing strategies: While LLMs often perform multiple scattered edits and tend to change meaning notably, humans rather encapsulate dependent changes in selfcontained, meaning-preserving edits.In this paper, we present a reinforcement learning approach that teaches LLMs human-like editing to improve the appropriateness of arguments.Our approach produces self-contained sentence-level edit suggestions that can be accepted or rejected independently.We train the approach using group relative policy optimization with a multi-component reward function that jointly optimizes edit-level semantic similarity, fluency, and pattern conformity as well as argument-level appropriateness.In automatic and human evaluation, it outperforms competitive baselines and the state of the art in humanlike editing, with multi-round editing achieving appropriateness close to full rewriting.
Institutions: Leibniz University Hannover, L3S Research Center
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166809376