arXiv：cs.CL· Meeri-Ly Muru, Eduard Barbu·· 3 小时前AI 评分33
爱沙尼亚语文档级文本简化：五大 LLM 评估与提示策略研究
Document-Level Text Simplification in Estonian Using Large Language Models
AI 导读
一项发表于 LREC 2026 的研究评估了五种多语言大语言模型在爱沙尼亚语文档级文本简化上的表现，考察了单次生成、模块化智能体流水线和指南增强流水线三种提示策略。结果显示 Gemini-2.0 和 LLaMA-3.3 输出接近母语流畅度且语义保持较强，其他模型存在明显语法与语义局限。研究还提出了新的文档级连贯性指标与可复现公开资源。
正文
Abstract:Document-level text simplification involves transformations that go beyond sentence-internal edits, addressing discourse coherence, anaphora resolution, and cross-paragraph consistency. Despite advances in sentence-level simplification for high-resource languages, document-level simplification in morphologically rich, low-resource languages such as Estonian remains largely unexplored. This study presents a comprehensive evaluation of five state-of-the-art multilingual large language models (LLMs) for document-level simplification in Estonian. Three prompting strategies are examined: single-pass generation, pipeline-based modular agents, and guideline-augmented pipelines. The evaluation framework integrates automatic metrics assessing readability, semantic preservation, and discourse coherence, alongside a structured manual annotation protocol. The findings indicate that Gemini-2.0 and LLaMA-3.3 produce outputs with near-native fluency and strong meaning preservation, whereas other models display notable grammatical and semantic limitations. This work contributes novel document-level coherence metrics, evidence-based prompting strategies, and publicly available resources for reproducibility.
| Comments: | 12 pages, 2 figures, 2 tables. Published at LREC 2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.10378 [cs.CL] |
| (or arXiv:2610.10378v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10378 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026), pp. 7225-7235, 2026 |
| Related DOI: | https://doi.org/10.63317/3ndqrcjckj32
DOI(s) linking to related resources |
Submission history
From: Eduard Barbu [view email]
[v1]
Wed, 7 Oct 2026 16:38:26 UTC (68 KB)
来源：arXiv：cs.CL · arxiv.org