홈 › Papers

A Framework for Automated Measurement of Responsible AI Harms in Generative AI Applications

2023-10-26 · Ahmed Magooda, Alec Helyar, Kyle Jackson, David Sullivan, Chad Atalla, Emily Sheng, Dan Vann, Richard Edgar, Hamid Palangi, Roman Lutz, Hongliang Kong, Vincent Yun, Eslam Kamal, Federico Zarfati, Hanna Wallach, Sarah Bird, Mei Chen

We present a framework for the automated measurement of responsible AI (RAI) metrics for large language models (LLMs) and associated products and services. Our framework for automatically measuring harms from LLMs builds on existing technical and sociotechnical expertise and leverages the capabilities of state-of-the-art LLMs, such as GPT-4. We use this framework to run through several case studies investigating how different LLMs may violate a range of RAI-related principles. The framework may be employed alongside domain-specific sociotechnical expertise to create measurements for new harm areas in the future. By implementing this framework, we aim to enable more advanced harm measurement efforts and further the responsible use of LLMs.

📄 PDF Abstract BibTeX arXiv:2310.17750

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Residual Connection 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Safety and Fairness for Content Moderation in Generative Models

2023-06-09 · Susan Hao, Piyush Kumar, Sarah Laszlo, Shivani Poddar 외

With significant advances in generative AI, new technologies are rapidly being deployed with generative components. Generative models are typically trained on large datasets, resulting in model behaviors that can mimic t…

Fairness

Taxonomizing Representational Harms using Speech Act Theory

2025-04-01 · Emily Corvi, Hannah Washington, Stefanie Reed, Chad Atalla 외

Representational harms are widely recognized among fairness-related harms caused by generative language systems. However, their definitions are commonly under-specified. We make a theoretical contribution to the specific…

Fairness valid

Not My Voice! A Taxonomy of Ethical and Safety Harms of Speech Generators

2024-01-25 · Wiebke Hutiri, Oresiti Papakyriakopoulos, Alice Xiang

The rapid and wide-scale adoption of AI to generate human speech poses a range of significant ethical and safety risks to society that need to be addressed. For example, a growing number of speech generation incidents ar…

Decision Making

Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)

2024-07-10 · Krishnaram Kenthapadi, Mehrnoosh Sameki, Ankur Taly

With the ongoing rapid adoption of Artificial Intelligence (AI)-based systems in high-stakes domains, ensuring the trustworthiness, safety, and observability of these systems has become crucial. It is essential to evalua…

Survey

Multi-Group Proportional Representation for Text-to-Image Models

2025-05-29 · Sangwon Jung, Alex Oesterling, Claudio Mayrink Verdun, Sajani Vithana 외

Text-to-image (T2I) generative models can create vivid, realistic images from textual descriptions. As these models proliferate, they expose new concerns about their ability to represent diverse demographic groups, propa…

Image Generation