# RLDE: A Reinforcement Learning Framework for Interpretable Iterative Document Editing

> Source: <https://www.machinebrief.com/news/rlde-a-reinforcement-learning-framework-for-interpretable-it-lzgc>
> Published: 2026-11-18 05:00:00+00:00

**Recommendation:** When optimizing document-editing agents on readability and perplexity, add a semantic-preservation penalty to the reward; RLDE kept 93% of meaning while cutting perplexity from 63.7 to 39.8.
More in the playbook "Evals and testing for LLM apps": <https://wpnews.pro/playbooks/evals-testing>

arXiv:2611.22039v1 Announce Type: new 
Abstract: Improving the quality, clarity, and flow of long documents remains a challenging problem in NLP, as human editing typically occurs through iterative refinement rather than a single-pass rewrite. Most existing automated systems act as black-box generators or rely on supervised learning, limiting interpretability and failing to capture the sequential nature of revisions. In this paper, we propose RLDE, an automated end-to-end metric-driven RL framework that formulates document revision as a reference-free MDP problem (unsupervised with respect to paired document-revision targets). Working with a limited action space (NOOP, INSERT, DELETE, REPLACE), RLDE leverages Pointer Networks for dynamic span selection at the token level and sends generative actions to the frozen BART-base model to obtain context-aware suggestions. PPO agents learn to optimize a multi-objective reward function based on readability, perplexity, and grammar metrics with the help of a novel SBERT-based Semantic Preservation Penalty constraint to avoid deletion degeneracy. Evaluations on the BEA-2019 dataset showed statistically significant results (p < 0.01) across all metrics, where Flesch Reading Ease increased from 49.8 to 59.4, perplexity decreased from 63.7 to 39.8, while preserving 93% of semantic information. When compared to Chain-of-Thought (CoT) prompt-engineered models like GPT-4 and LLaMA-2, RLDE shows high performance at a very low computational inference cost. Moreover, the quality of edits generated by RLDE has been verified via human evaluations, scoring 4.9/5 for meaning preservation and 4.4/5 for edit quality.
