paper-with-me

Papers

LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language Model

2025-08-07 · Tao Sun, Oliver Liu, JinJin Li, Lan Ma arxiv

Multimodal generative AI usually involves generating image or text responses given inputs in another modality. The evaluation of image-text relevancy is essential for measuring response quality or ranking candidate responses. In particular, binary relevancy evaluation, i.e., `Relevant'' vs. `Not Relevant'', is a fundamental problem. However, this is a challenging task considering that texts have diverse formats and the definition of relevancy varies in different scenarios. We find that Multimodal Large Language Models (MLLMs) are an ideal choice to build such evaluators, as they can flexibly handle complex text formats and take in additional task information. In this paper, we present LLaVA-RE, a first attempt for binary image-text relevancy evaluation with MLLM. It follows the LLaVA architecture and adopts detailed task instructions and multimodal in-context samples. In addition, we propose a novel binary relevancy data set that covers various tasks. Experimental results validate the effectiveness of our framework.

📄 PDF Abstract BibTeX arXiv:2508.05602

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation

2025-07-28 · Shijie Zhou, Ruiyi Zhang, Huaisheng Zhu, Branislav Kveton 외 arxiv

We introduce LLaVA-Reward, an efficient reward model designed to automatically evaluate text-to-image (T2I) generations across multiple perspectives, leveraging pretrained multimodal large language models (MLLMs). Existi…

Text-to-Image Generation

DS@GT eRisk 2024: Sentence Transformers for Social Media Risk Assessment

2024-07-10 · David Guecha, Aaryan Potdar, Anthony Miyaguchi

We present working notes for DS@GT team in the eRisk 2024 for Tasks 1 and 3. We propose a ranking system for Task 1 that predicts symptoms of depression based on the Beck Depression Inventory (BDI-II) questionnaire using…

Sentence

LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding

2023-06-29 · Yanzhe Zhang, Ruiyi Zhang, Jiuxiang Gu, Yufan Zhou 외

Instruction tuning unlocks the superior capability of Large Language Models (LLM) to interact with humans. Furthermore, recent instruction-following datasets include images as visual inputs, collecting responses for imag…

16kImage CaptioningInstruction FollowingOptical Character Recognition (OCR)+1

MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction

2021-06-24 · Guozhi Tang, Lele Xie, Lianwen Jin, Jiapeng Wang 외

Visual Information Extraction (VIE) task aims to extract key information from multifarious document images (e.g., invoices and purchase receipts). Most previous methods treat the VIE task simply as a sequence labeling pr…

Graph Neural Network

DF-LLaVA: Unlocking MLLMs for Synthetic Image Detection via Knowledge Injection and Conflict-Driven Self-Reflection

2025-09-18 · Zhuokang Shen, Kaisen Zhang, Bohan Jia, Heming Jia 외 arxiv

With the increasing prevalence of synthetic images, evaluating image authenticity and locating forgeries accurately while maintaining human interpretability remains a challenging task. Existing detection models primarily…