White Paper - Creating a Repository of Objectionable Online Content: Addressing Undesirable Biases and Ethical Considerations
This white paper summarizes the authors' structured brainstorming regarding ethical considerations for creating an extensive repository of online content labeled with tags that describe potentially questionable content for young viewers. The workshop focused on four topics: 1) identifying risks for unintended biases in the data and labels, 2) how to reduce risks for unintended biases; 3) identifying ethical considerations of the annotation task, and 4) reducing the risks for the annotators.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
White Paper: Challenges and Considerations for the Creation of a Large Labelled Repository of Online Videos with Questionable Content
This white paper presents a summary of the discussions regarding critical considerations to develop an extensive repository of online videos annotated with labels indicating questionable content. The main discussion poin…
Universal and Transferable Adversarial Attacks on Aligned Language Models
Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While ther…
Adversarial AttackIngenuityAnswering Yes-No Questions by Penalty Scoring in History Subjects of University Entrance Examinations
Answering yes{--}no questions is more difficult than simply retrieving ranked search results. To answer yes{--}no questions, especially when the correct answer is no, one must find an objectionable keyword that makes the…
Question AnsweringOnline Personalizing White-box LLMs Generation with Neural Bandits
The advent of personalized content generation by LLMs presents a novel challenge: how to efficiently adapt text to meet individual preferences without the unsustainable demand of creating a unique model for each user. Th…
Headline GenerationText GenerationEfficient Neural Network based Classification and Outlier Detection for Image Moderation using Compressed Sensing and Group Testing
Popular social media platforms employ neural network based image moderation engines to classify images uploaded on them as having potentially objectionable content. Such moderation engines must answer a large number of q…
compressed sensingEfficient Neural NetworkOutlier Detection