paper-with-me

Papers

Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansion

2024-12-31 · Hebin Wang, Yangning Li, Yinghui Li, Hai-Tao Zheng, Wenhao Jiang, Hong-Gee Kim

The rapid development of multimodal large language models (MLLMs) has brought significant improvements to a wide range of tasks in real-world applications. However, LLMs still exhibit certain limitations in extracting implicit semantic information. In this paper, we apply MLLMs to the Multi-modal Entity Set Expansion (MESE) task, which aims to expand a handful of seed entities with new entities belonging to the same semantic class, and multi-modal information is provided with each entity. We explore the capabilities of MLLMs to understand implicit semantic information at the entity-level granularity through the MESE task, introducing a listwise ranking method LUSAR that maps local scores to global rankings. Our LUSAR demonstrates significant improvements in MLLM's performance on the MESE task, marking the first use of generative MLLM for ESE tasks and extending the applicability of listwise ranking.

📄 PDF Abstract BibTeX arXiv:2501.00330

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language Models

2025-08-12 · Wei Cai, Jian Zhao, Yuchu Jiang, Tianle Zhang 외 arxiv

Large Vision-Language Models face growing safety challenges with multimodal inputs. This paper introduces the concept of Implicit Reasoning Safety, a vulnerability in LVLMs. Benign combined inputs trigger unsafe LVLM out…

Set-CLIP: Exploring Aligned Semantic From Low-Alignment Multimodal Data Through A Distribution View

2024-06-09 · Zijia Song, Zelin Zang, Yelin Wang, Guozheng Yang 외

Multimodal fusion breaks through the boundaries between diverse modalities and has already achieved notable performances. However, in many specialized fields, it is struggling to obtain sufficient alignment data for trai…

Exploring multimodal implicit behavior learning for vehicle navigation in simulated cities

2025-09-18 · Eric Aislan Antonelo, Gustavo Claudio Karl Couto, Christian Möller arxiv

Standard Behavior Cloning (BC) fails to learn multimodal driving decisions, where multiple valid actions exist for the same scenario. We explore Implicit Behavioral Cloning (IBC) with Energy-Based Models (EBMs) to better…

Exploring Implicit Visual Misunderstandings in Multimodal Large Language Models through Attention Analysis

2025-05-15 · Pengfei Wang, Guohai Xu, Weinong Wang, Junjie Yang 외

Recent advancements have enhanced the capability of Multimodal Large Language Models (MLLMs) to comprehend multi-image information. However, existing benchmarks primarily evaluate answer correctness, overlooking whether …

How to Understand "Support"? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding

2024-02-29 · Jiamin Luo, Jianing Zhao, Jingjing Wang, Guodong Zhou

Weakly-supervised Phrase Grounding (WPG) is an emerging task of inferring the fine-grained phrase-region matching, while merely leveraging the coarse-grained sentence-image pairs for training. However, existing studies o…

Causal InferencecounterfactualImplicit RelationsPhrase Grounding+1