paper-with-me

홈 › Papers

Better Verified Explanations with Applications to Incorrectness and Out-of-Distribution Detection

2024-09-04 · Min Wu, Xiaofu Li, Haoze Wu, Clark Barrett

Building on VeriX (Verified eXplainability, arXiv:2212.01051), a system for producing optimal verified explanations for machine learning model outputs, we present VeriX+, which significantly improves both the size and the generation time of verified explanations. We introduce a bound propagation-based sensitivity technique to improve the size, and a binary search-based traversal with confidence ranking for improving time -- the two techniques are orthogonal and can be used independently or together. We also show how to adapt the QuickXplain (Junker 2004) algorithm to our setting to provide a trade-off between size and time. Experimental evaluations on standard benchmarks demonstrate significant improvements on both metrics, e.g., a size reduction of 38% on the GTSRB dataset and a time reduction of 90% on MNIST. We also explore applications of our verified explanations and show that explanation size is a useful proxy for both incorrectness detection and out-of-distribution detection.

📄 PDF Abstract BibTeX arXiv:2409.03060

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Detection

Similar Papers 제목 키워드 기반

On Incorrectness Logic and Kleene Algebra with Top and Tests

2021-08-17 · Cheng Zhang, Arthur Azevedo de Amorim, Marco Gaboardi

Kleene algebra with tests (KAT) is a foundational equational framework for reasoning about programs, which has found applications in program transformations, networking and compiler optimizations, among many other areas.…

Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment

2022-04-06 · Findings (ACL) 2022 5 · Zichao Li, Prakhar Sharma, Xing Han Lu, Jackie C. K. Cheung 외

Most research on question answering focuses on the pre-deployment stage; i.e., building an accurate model for deployment. In this paper, we ask the question: Can we improve QA systems further \emph{post-}deployment based…

Overall - TestQuestion AnsweringRetrieval

Faster Verified Explanations for Neural Networks

2025-11-28 · Alessandro De Palma, Greta Dolcetti, Caterina Urban arxiv

Verified explanations are a principled way to explain the decisions taken by neural networks, which are otherwise black-box in nature. However, these techniques face significant scalability challenges, as they require mu…

Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Most research on question answering focuses on the pre-deployment stage; i.e., building an accurate model for deployment. In this paper, we ask the question: Can we improve QA systems further post-deployment based on use…

Question AnsweringRetrieval

ChatGPT Incorrectness Detection in Software Reviews

2024-03-25 · Minaoar Hossain Tanzil, Junaed Younus Khan, Gias Uddin

We conducted a survey of 135 software engineering (SE) practitioners to understand how they use Generative AI-based chatbots like ChatGPT for SE tasks. We find that they want to use ChatGPT for SE tasks like software lib…