LexLattice: Multilingual Extractive Summarization via Neural Cellular Automata on Document Hierarchies

2026-09-22

AI Summary

本文提出LexLattice，通过在文档层次结构上应用神经元细胞自动机解决法律文本摘要中的保真度问题，实现了多语言和跨语言环境下的最佳性能。

Abstract

Faithfulness is a central concern in legal text summarization, which motivates extractive approaches that select verbatim content traceable to its source. Such methods typically rank paragraphs or other structural units in isolation, yet give little attention to consolidating evidence that is distributed across, and shares salience between, distant parts of a document. We introduce LexLattice, an extractive summarizer that reifies a legal act's hierarchy as a two-dimensional semantic lattice and consolidates over it with a masked 2D neural cellular automata before selection. LexLattice attains state-of-the-art ROUGE across all 24 languages of EUR-Lex-Sum in both multilingual and cross-lingual settings, surpassing instruction-tuned baselines with billions of parameters, despite concentrating all trainable capacity in a 1.8M parameter consolidator over a frozen multilingual encoder. A consolidator trained only on high-resource languages further transfers to unseen languages with near-lossless retention (0.99), indicating that the model operates on language-agnostic semantic geometry rather than surface form. Our results position explicit consolidation over document structure as a compact and traceable alternative to scale for multilingual legal summarization.

Problem

• faithfulness
• legal text summarization
• extractive approaches
• document structure
• evidence consolidation

Innovation

• neural cellular automata
• document hierarchy
• multilingual summarization
• semantic lattice