Results 81 to 90 of about 50,001 (113)

Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability

Annual Meeting of the Association for Computational Linguistics
While large language models (LLMs) show promise in code generation, existing benchmarks neglect the flowchart-based code generation. To promote further research on flowchart-based code generation, this work presents Flow2Code, a novel benchmark for ...
Mengliang He, Jiayi Zeng, Yankai Jiang, Wei Zhang, Zeming Liu, Xiaoming Shi, Aimin Zhou   +6 more
semanticscholar   +1 more source

FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding

European Conference on Artificial Intelligence
Flowcharts are graphical tools for representing complex concepts in concise visual representations. This paper introduces the FlowLearn dataset, a resource tailored to enhance the understanding of flowcharts.
Huitong Pan, Qi Zhang, Cornelia Caragea, E. Dragut, Longin Jan Latecki   +4 more
semanticscholar   +1 more source

Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents

Conference on Empirical Methods in Natural Language Processing
Flowcharts are a critical tool for visualizing decision-making processes. However, their non-linear structure and complex visual-textual relationships make it challenging to interpret them using LLMs, as vision-language models frequently hallucinate ...
Manan Suri, Puneet Mathur, Nedim Lipka, Franck Dernoncourt, Ryan A. Rossi, V. Gupta, Dinesh Manocha   +6 more
semanticscholar   +1 more source

Multimodal Large Language Model With Knowledge Retrieval Using Flowchart Embedding for Forming Follow-Up Recommendations for Pancreatic Cystic Lesions.

AJR. American journal of roentgenology
Background: The American College of Radiology (ACR) Incidental Findings Committee (IFC) algorithm provides guidance for pancreatic cystic lesions (PCL) management.
Zhe-Ren Zhu, Jin Liu, C. Hong, Sina Houshmand, Kang Wang, Yang Yang   +5 more
semanticscholar   +1 more source

Arrow-Guided VLM: Enhancing Flowchart Understanding via Arrow Direction Encoding

arXiv.org
Flowcharts are indispensable tools in software design and business-process analysis, yet current vision-language models (VLMs) frequently misinterpret the directional arrows and graph topology that set these diagrams apart from natural images.
Takamitsu Omasa, Ryo Koshihara, Masumi Morishige   +2 more
semanticscholar   +1 more source

Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding

arXiv.org
Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. However, two key challenges arise: (i) Limited controllability--users have minimal influence over the ...
Junyi Ye, Ankan Dash, Wenpeng Yin, G. Wang   +3 more
semanticscholar   +1 more source

Validation of a diagnostic flowchart for tuberculous pleurisy in pleural fluid with high levels of adenosine deaminase.

Respiratory Investigation
INTRODUCTION Adenosine deaminase (ADA) in pleural fluid is a useful marker for diagnosing tuberculous pleurisy. However, recent studies have reported a lower specificity of pleural fluid ADA levels.
M. Shimoda, Yoshiaki Tanaka, Takashi Ohe, Takashi Ishiguro, Atsushi Suzuki, Y. Kurahara, Yasuaki Shimatani, Hidekazu Matsushima, K. Kusano, Hiroki Ohta, Satoru Yanagisawa, Yuki Kozu, Yui Takaya, Shunya Igarashi, Y. Kimizuka, Kojiro Honda, S. Otani, Shigeki Chiba, Dong-Jie Xu, M. Mitsui, Y. Waseda, H. Ishii   +21 more
semanticscholar   +1 more source

Code Insight - Flowchart Generator

Journées Francophones d'Ingénierie des Connaissances
The goal of the project is to automate the conversion of pseudocode into visually appealing flowcharts, facilitating the transition from human-readable algorithm descriptions to machine-executable code in software. This study presents a new approach that
Abhay Chopade, Vaibhav Shingde, Aman Chavare, Tejas Bhagwat   +3 more
semanticscholar   +1 more source

Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework

The Web Conference
Customer service automation has seen growing demand within digital transformation. Existing approaches either rely on modular system designs with extensive agent orchestration or employ over-simplified instruction schemas, providing limited guidance and ...
Mengze Hong, Chen Zhang, Zi-Chang Guo, Han-Lin Gu, Di Jiang, Qing Li   +5 more
semanticscholar   +1 more source

First Multi-Dimensional Evaluation of Flowchart Comprehension for Multimodal Large Language Models

arXiv.org
With the development of Multimodal Large Language Models (MLLMs) technology, its general capabilities are increasingly powerful. To evaluate the various abilities of MLLMs, numerous evaluation systems have emerged.
En-Ming Zhang, Ruobing Yao, Huanyong Liu, Junhui Yu, Jia-Le Wang   +4 more
semanticscholar   +1 more source