AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Explainable Oracle Bone Script Recognition via Multimodal Pictographic Reasoning

Yin Wu, Zhengxuan Zhang, Jiayu Chen, Chang Xu, Yuyu Luo, Nan Tang, Hui Xiong

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an explainable oracle bone script recognition approach using multimodal pictographic reasoning, moving beyond opaque classification of glyphs.

Problem

Oracle bone script recognition systems are accurate classifiers but treat glyphs as opaque data, ignoring their pictographic nature and failing to make recognition explainable to the public.

Approach

Frames oracle bone script recognition as multimodal pictographic reasoning so that predictions come with explanations grounded in the glyphs' visual metaphors (abstract only; method details not available).

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add stage 2 multimodal adaptation (glyph and real-world images) after domain adaptation (ablation)OBS-VM · OracleVis test setPictographic Rationality (human): 2.31 -> 3.79Improved
add stage 2 multimodal adaptation (ablation)OBS-VM · OracleVis test setTop-1 accuracy: 0.13 -> 0.23Improved
add stage 2 multimodal adaptation (ablation)OBS-VM · OracleVis test setTop-5 accuracy: 0.16 -> 0.33Improved
two-stage fine-tuning on OracleVisQwen2-VL-7B · OracleVis test setPictographic Rationality (human): 2.37 -> 3.79Improved
fine-tune Qwen2-VL-7B on OracleVis instead of using GPT-4oOBS-VM · OracleVis test setTop-1 accuracy: 0.17 -> 0.23Improved
fine-tune on OracleVis vs GPT-4oOBS-VM · OracleVis test setSemantic Rationality (human): 4.29 -> 4.33Improved
OBS-VM vs human expert-style explanationsOBS-VM · 50 shared glyphsPictographic Rationality: 4.20 -> 3.78Hurt
OBS-VM vs human explanations on readabilityOBS-VM · 50 shared glyphsReadability: 4.30 -> 4.28No clear effect
interactive learning with OBS-VM vs static web resourcesnon-expert learners · User study (N=24)Understanding gain (/10): +1.7 -> +5.5Improved
interactive learning with OBS-VM vs static web resourcesnon-expert learners · User study (N=24)Interest gain (/5): +0.4 -> +1.9Improved
interactive learning with OBS-VM vs static web resourcesnon-expert learners · User study (N=24)Confidence gain (/5): +0.3 -> +2.0Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy