Verification Task
Verification tasks in various fields aim to ensure the accuracy, reliability, and trustworthiness of systems and models. Current research focuses on developing robust verification methods across diverse domains, including image and document analysis (using recurrent and transformer-based models), logical reasoning (employing LLMs and symbolic methods), and autonomous systems (leveraging formal methods and data-driven approaches). These advancements are crucial for enhancing the safety and dependability of AI systems, robotic applications, and other technologies where reliable performance is paramount.
Papers
Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition
Majeed Kazemitabaar, Jack Williams, Ian Drosos, Tovi Grossman, Austin Henley, Carina Negreanu, Advait Sarkar
RVISA: Reasoning and Verification for Implicit Sentiment Analysis
Wenna Lai, Haoran Xie, Guandong Xu, Qing Li
Enhanced Bank Check Security: Introducing a Novel Dataset and Transformer-Based Approach for Detection and Verification
Muhammad Saif Ullah Khan, Tahira Shehzadi, Rabeya Noor, Didier Stricker, Muhammad Zeshan Afzal
VeriFlow: Modeling Distributions for Neural Network Verification
Faried Abu Zaid, Daniel Neider, Mustafa Yalçıner
Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving
Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas
Verification of Population Protocols with Unordered Data
Steffen van Bergerem, Roland Guttenberg, Sandra Kiefer, Corto Mascle, Nicolas Waldburger, Chana Weil-Kennedy