Towards More Trustworthy Deep Code Models by Enabling Out-of-Distribution Detection
Numerous machine learning (ML) models have been developed, including those for
software engineering (SE) tasks, under the assumption that training and testing data come …
software engineering (SE) tasks, under the assumption that training and testing data come …
FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA
SM Sarwar - arxiv preprint arxiv:2502.18536, 2025 - arxiv.org
Visual Question Answering requires models to generate accurate answers by integrating
visual and textual understanding. However, VQA models still struggle with hallucinations …
visual and textual understanding. However, VQA models still struggle with hallucinations …
LLaVA 를 활용한 분포 외 데이터 탐지
이영환， 유창동 - 대한전자공학회 학술대회, 2024 - dbpia.co.kr
In this paper, we introduce LLaVA-OOD, an Out-of-Distribution (OOD) detection method
using pre-trained Multimodal Large Language Models (MLLMs). This method employs the …
using pre-trained Multimodal Large Language Models (MLLMs). This method employs the …