Work

CogEvolve: A Multimodal Benchmark for Evaluating Relational Reasoning in Semantic Extension

Year: 2026

Type: conference-paper

Abstract: Human cognition excels at extending knowledge through analogy, where word meanings evolve along structured pathways from concrete prototypes to abstract senses via metaphor and metonymy.Do Large Language Models (LLMs) internalize this generative logic, or merely mimic statistical patterns?To investigate this, we introduce CogEvolve, a cognitive linguistic benchmark designed to test these evolutionary pathways across textual and visual modalities.Our evaluation reveals a distinct cognitive profile: models function as "Super-Associators" expert at static recognition yet fail at causal reasoning.In text, they exhibit a Frequency-Primacy Conflation, confusing statistical prevalence with cognitive basicness.Crucially, this reasoning collapses further in the visual domain.We term this deficit the Ungrounded Arrow: models possess high-fidelity concept representations (the "dots") but lack the transformational operators (the "arrows") essential for true relational understanding 1 .

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2026.acl-long.1190

Authors: Jingjie Zeng, Huayang Li, Liang Yang, Yuanyuan Sun, Shaowu Zhang, Hongfei Lin

Institution: Dalian University of Technology

Language: English

Topic: Multimodal Machine Learning Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities

Awards: G3819115411, G8812420149