AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Chinese Two-part Allegorical Sayings Reading Comprehension: Exploration from Reasoning to Metaphor

Dongyu Su, Yimin Xiao, Tongguan Wang, Feiyue Xue, Junkai Li, Hui Liu, Ying Sha

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 0 citations (OpenAlex)

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.

Introduces a reading comprehension benchmark for Chinese two-part allegorical sayings (TPAS) to probe semantic rhetoric, logical reasoning, and metaphor understanding.

Problem

Existing research uses Chinese two-part allegorical sayings (TPAS) mainly to assist other semantic tasks and lacks in-depth exploration of their intrinsic mechanisms: semantic rhetoric, logical reasoning, and metaphorical expression.

Approach

Constructs the first Chinese TPAS reading comprehension dataset to study the riddle-explanation structure of TPAS as a testbed for reasoning and metaphor understanding.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add joint vector cross-projection (ablation)MTCLN · CTRC (average over five sets)Avg-Acc (%): 66.96 -> 67.47Improved
add softened contrastive learning (ablation)MTCLN · CTRC (average over five sets)Avg-Acc (%): 59.18 -> 67.47Improved
add multi-view feature fusion (ablation)MTCLN · CTRC (average over five sets)Avg-Acc (%): 66.78 -> 67.47Improved
add softened contrastive learning on top of JP+MF (ablation)MTCLN · CTRC (average over five sets)Avg-Acc (%): 54.66 -> 67.47Improved
add multi-view fusion and softened contrastive learning together (no JP) (ablation)MTCLN · CTRC (average over five sets)Avg-Acc (%): 58.82 -> 67.47Improved
add all three modules to RoBERTa baseline (ablation)MTCLN · CTRC (average over five sets)Avg-Acc (%): 52.70 -> 67.47Improved
add softened contrastive learning (ablation)MTCLN · CTRC Sim setaccuracy (%): 46.51 -> 58.34Improved
add joint vector cross-projection (ablation)MTCLN · CTRC testaccuracy (%): 72.89 -> 73.13Improved
few-shot prompting of GPT-4o with more examplesGPT-4o-20241120 · CTRC testaccuracy (%): 42.94 -> 43.52 -> 46.32 -> 44.85Mixed
use MTCLN instead of LoRA-tuned DeepSeek-R1-1.5B / GPT-4oMTCLN · CTRC (average over five sets)Avg-Acc (%): outperforming LLMs by 25.48%Improved

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