Identity-related Speech Suppression in Generative AI Content Moderation

• URL: http://arxiv.org/abs/2409.13725v1
• Date: Mon, 9 Sep 2024 14:34:51 GMT
• Title: Identity-related Speech Suppression in Generative AI Content Moderation
• Authors: Oghenefejiro Isaacs Anigboro, Charlie M. Crawford, Danaë Metaxa, Sorelle A. Friedler,
• Abstract summary: Generative AI systems now use such filters to keep undesired generated content from being created by or shown to users. In this paper, we define and introduce measures of speech suppression, focusing on speech related to different identity groups incorrectly filtered by a range of content moderation APIs. We find that identity-related speech is more likely to be incorrectly filtered than other speech except in the cases of a few non-marginalized groups.
• Score: 2.812395851874055
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Automated content moderation has long been used to help identify and filter undesired user-generated content online. Generative AI systems now use such filters to keep undesired generated content from being created by or shown to users. From classrooms to Hollywood, as generative AI is increasingly used for creative or expressive text generation, whose stories will these technologies allow to be told, and whose will they suppress? In this paper, we define and introduce measures of speech suppression, focusing on speech related to different identity groups incorrectly filtered by a range of content moderation APIs. Using both short-form, user-generated datasets traditional in content moderation and longer generative AI-focused data, including two datasets we introduce in this work, we create a benchmark for measurement of speech suppression for nine identity groups. Across one traditional and four generative AI-focused automated content moderation services tested, we find that identity-related speech is more likely to be incorrectly suppressed than other speech except in the cases of a few non-marginalized groups. Additionally, we find differences between APIs in their abilities to correctly moderate generative AI content.

Related papers

• Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing [55.2480439325792]
  Misclassification can lead to false plagiarism accusations and misleading claims about AI prevalence in online content. We systematically evaluate eleven state-of-the-art AI-text detectors using our AI-Polished-Text Evaluation dataset. Our findings reveal that detectors frequently misclassify even minimally polished text as AI-generated, struggle to differentiate between degrees of AI involvement, and exhibit biases against older and smaller models.
  arXiv  Detail & Related papers  (2025-02-21T18:45:37Z)
• Detecting Document-level Paraphrased Machine Generated Content: Mimicking Human Writing Style and Involving Discourse Features [57.34477506004105]
  Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation. We introduce novel methodologies and datasets to overcome these challenges. We propose MhBART, an encoder-decoder model designed to emulate human writing style. We also propose DTransformer, a model that integrates discourse analysis through PDTB preprocessing to encode structural features.
  arXiv  Detail & Related papers  (2024-12-17T08:47:41Z)
• A Unified Multi-Task Learning Architecture for Hate Detection Leveraging User-Based Information [23.017068553977982]
  Hate speech, offensive language, aggression, racism, sexism, and other abusive language are common phenomena in social media. There is a need for Artificial Intelligence(AI)based intervention which can filter hate content at scale. This paper introduces a unique model that improves hate speech identification for the English language by utilising intra-user and inter-user-based information.
  arXiv  Detail & Related papers  (2024-11-11T10:37:11Z)
• A Target-Aware Analysis of Data Augmentation for Hate Speech Detection [3.858155067958448]
  Hate speech is one of the main threats posed by the widespread use of social networks. We investigate the possibility of augmenting existing data with generative language models, reducing target imbalance. For some hate categories such as origin, religion, and disability, hate speech classification using augmented data for training improves by more than 10% F1 over the no augmentation baseline.
  arXiv  Detail & Related papers  (2024-10-10T15:46:27Z)
• Unlearning Targeted Information via Single Layer Unlearning Gradient [15.374381635334897]
  Unauthorized privacy-related computation is a significant concern for society. The EU's General Protection Regulation includes a "right to be forgotten" We propose Single Layer Unlearning Gradient (SLUG) to unlearn targeted information by updating targeted layers of a model.
  arXiv  Detail & Related papers  (2024-07-16T15:52:36Z)
• Classifying Human-Generated and AI-Generated Election Claims in Social Media [8.990994727335064]
  Malicious actors may use social media to disseminate misinformation to undermine trust in the electoral process. The emergence of Large Language Models (LLMs) exacerbates this issue by enabling malicious actors to generate misinformation at an unprecedented scale. We present a novel taxonomy for characterizing election-related claims.
  arXiv  Detail & Related papers  (2024-04-24T18:13:29Z)
• Let AI Entertain You: Increasing User Engagement with Generative AI and Rejection Sampling [7.715423424826709]
  This paper presents a generic framework of how to improve user engagement with generative AI by leveraging user feedback. We leveraged the framework in the context of email notification subject lines generation for an online social network. This represents an early milestone in the industry's successful use of generative AI to enhance user engagement.
  arXiv  Detail & Related papers  (2023-12-16T08:06:12Z)
• Evaluation of Speaker Anonymization on Emotional Speech [9.223908421919733]
  Speech data carries a range of personal information, such as the speaker's identity and emotional state. Current studies have addressed the topic of preserving speech privacy. The VoicePrivacy 2020 Challenge (VPC) is about speaker anonymization.
  arXiv  Detail & Related papers  (2023-04-15T20:50:29Z)
• Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense [56.077252790310176]
  We present a paraphrase generation model (DIPPER) that can paraphrase paragraphs, condition on surrounding context, and control lexical diversity and content reordering. Using DIPPER to paraphrase text generated by three large language models (including GPT3.5-davinci-003) successfully evades several detectors, including watermarking. We introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider.
  arXiv  Detail & Related papers  (2023-03-23T16:29:27Z)
• Hate Speech and Offensive Language Detection using an Emotion-aware Shared Encoder [1.8734449181723825]
  Existing works on hate speech and offensive language detection produce promising results based on pre-trained transformer models. This paper addresses a multi-task joint learning approach which combines external emotional features extracted from another corpora. Our findings demonstrate that emotional knowledge helps to more reliably identify hate speech and offensive language across datasets.
  arXiv  Detail & Related papers  (2023-02-17T09:31:06Z)
• Countering Malicious Content Moderation Evasion in Online Social Networks: Simulation and Detection of Word Camouflage [64.78260098263489]
  Twisting and camouflaging keywords are among the most used techniques to evade platform content moderation systems. This article contributes significantly to countering malicious information by developing multilingual tools to simulate and detect new methods of evasion of content.
  arXiv  Detail & Related papers  (2022-12-27T16:08:49Z)
• An Attribute-Aligned Strategy for Learning Speech Representation [57.891727280493015]
  We propose an attribute-aligned learning strategy to derive speech representation that can flexibly address these issues by attribute-selection mechanism. Specifically, we propose a layered-representation variational autoencoder (LR-VAE), which factorizes speech representation into attribute-sensitive nodes. Our proposed method achieves competitive performances on identity-free SER and a better performance on emotionless SV.
  arXiv  Detail & Related papers  (2021-06-05T06:19:14Z)
• Data Expansion using Back Translation and Paraphrasing for Hate Speech Detection [1.192436948211501]
  We present a new deep learning-based method that fuses a Back Translation method, and a Paraphrasing technique for data augmentation. We evaluate our proposal on five publicly available datasets; namely, AskFm corpus, Formspring dataset, Warner and Waseem dataset, Olid, and Wikipedia toxic comments dataset.
  arXiv  Detail & Related papers  (2021-05-25T09:52:42Z)
• Protecting gender and identity with disentangled speech representations [49.00162808063399]
  We show that protecting gender information in speech is more effective than modelling speaker-identity information. We present a novel way to encode gender information and disentangle two sensitive biometric identifiers.
  arXiv  Detail & Related papers  (2021-04-22T13:31:41Z)
• On the Impact of Word Error Rate on Acoustic-Linguistic Speech Emotion Recognition: An Update for the Deep Learning Era [0.0]
  We create transcripts from the original speech by applying three modern ASR systems. For extraction and learning of acoustic speech features, we utilise openSMILE, openXBoW, DeepSpectrum, and auDeep. We achieve state-of-the-art unweighted average recall values of $73.6,%$ and $73.8,%$ on the speaker-independent development and test partitions of IEMOCAP.
  arXiv  Detail & Related papers  (2021-04-20T17:10:01Z)
• Speaker De-identification System using Autoencoders and Adversarial Training [58.720142291102135]
  We propose a speaker de-identification system based on adversarial training and autoencoders. Experimental results show that combining adversarial learning and autoencoders increase the equal error rate of a speaker verification system.
  arXiv  Detail & Related papers  (2020-11-09T19:22:05Z)
• PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation [92.7366819044397]
  Self-supervised pre-training has emerged as a powerful technique for natural language understanding and generation. This work presents PALM with a novel scheme that jointly pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus. An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks.
  arXiv  Detail & Related papers  (2020-04-14T06:25:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.