Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors

TL;DR

HieroSA is a novel framework that enables multimodal models to analyze hieroglyphic characters at the stroke level without language-specific prior knowledge.

Contribution

It introduces a generalizable method to extract stroke-level structures from hieroglyphs directly from images, enhancing structural understanding across scripts.

Findings

HieroSA effectively captures internal character structures and semantics.

The method generalizes across modern and ancient hieroglyphs.

Experimental results show improved structural analysis without handcrafted data.

Abstract

Hieroglyphs, as logographic writing systems, encode rich semantic and cultural information within their internal structural composition. Yet, current advanced Large Language Models (LLMs) and Multimodal LLMs (MLLMs) usually remain structurally blind to this information. LLMs process characters as textual tokens, while MLLMs additionally view them as raw pixel grids. Both fall short to model the underlying logic of character strokes. Furthermore, existing structural analysis methods are often script-specific and labor-intensive. In this paper, we propose Hieroglyphic Stroke Analyzer (HieroSA), a novel and generalizable framework that enables MLLMs to automatically derive stroke-level structures from character bitmaps without handcrafted data. It transforms modern logographic and ancient hieroglyphs character images into explicit, interpretable line-segment representations in a normalized coordinate space, allowing for cross-lingual generalization. Extensive experiments demonstrate that HieroSA effectively captures character-internal structures and semantics, bypassing the need for language-specific priors. Experimental results highlight the potential of our work as a graphematics analysis tool for a deeper understanding of hieroglyphic scripts. View our code at https://github.com/THUNLP-MT/HieroSA.