paper-with-me

홈 › Papers

GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection

2025-08-23 · Melissa Kazemi Rad, Alberto Purpura, Himanshu Kumar, Emily Chen, Mohammad Shahed Sorower arxiv

We address the problem of data scarcity in harmful text classification for guardrailing applications and introduce GRAID (Geometric and Reflective AI-Driven Data Augmentation), a novel pipeline that leverages Large Language Models (LLMs) for dataset augmentation. GRAID consists of two stages: (i) generation of geometrically controlled examples using a constrained LLM, and (ii) augmentation through a multi-agentic reflective process that promotes stylistic diversity and uncovers edge cases. This combination enables both reliable coverage of the input space and nuanced exploration of harmful content. Using two benchmark data sets, we demonstrate that augmenting a harmful text classification dataset with GRAID leads to significant improvements in downstream guardrail model performance.

📄 PDF Abstract BibTeX arXiv:2508.17057

Code (0)

등록된 구현이 없습니다.

Tasks

Synthetic Data GenerationText ClassificationData Augmentation

Similar Papers 제목 키워드 기반

GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data Generation

2025-10-25 · Karim Elmaaroufi, Liheng Lai, Justin Svegliato, Yutong Bai 외 arxiv

Vision Language Models (VLMs) achieve strong performance on many vision-language tasks but often struggle with spatial reasoning$\unicode{x2014}$a prerequisite for many applications. Empirically, we find that a dataset p…

Spatial Reasoning3D Reconstruction

Generative Responsible AI Data Evaluation Schema (GRAIDES) for AI Assurance in Local Government

2026-06-18 · Ethan Knights, Christopher Conlan, Temilorun Gbolahan, Stephen Waterman 외 arxiv

Trust in the application of generative Artificial Intelligence (AI) relies on well-governed measurable evidence of performance and safety. In practice, however, evaluation data is often fragmented across systems, inconsi…

Generating Realistic Forehead-Creases for User Verification via Conditioned Piecewise Polynomial Curves

2025-01-23 · Abhishek Tandon, Geetanjali Sharma, Gaurav Jaswal, Aditya Nigam 외

We propose a trait-specific image generation method that models forehead creases geometrically using B-spline and B\'ezier curves. This approach ensures the realistic generation of both principal creases and non-prominen…

DiversityImage Generation

REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints

2025-03-09 · Di wu, Liu Liu, Zhou Linli, Anran Huang 외

Articulated objects, as prevalent entities in human life, their 3D representations play crucial roles across various applications. However, achieving both high-fidelity textured surface reconstruction and dynamic generat…

Surface Reconstruction

Simultaneous Diffusion Sampling for Conditional LiDAR Generation

2024-10-15 · Ryan Faulkner, Luke Haub, Simon Ratcliffe, Anh-Dzung Doan 외

By enabling capturing of 3D point clouds that reflect the geometry of the immediate environment, LiDAR has emerged as a primary sensor for autonomous systems. If a LiDAR scan is too sparse, occluded by obstacles, or too …