Whisper Speech-to-Text AI Reportedly Found to Create Violent Hallucinations
Description
Researchers at Cornell reportedly found that OpenAI's Whisper, a speech-to-text system, can hallucinate violent language and fabricated details, especially with long pauses in speech, such as from those with speech impairments. Analyzing 13,000 clips, they determined 1% contained harmful hallucinations. These errors pose risks in hiring, legal trials, and medical documentation. The study suggests improving model training to reduce these hallucinations for diverse speaking patterns.
Actors
Alleged Deployers
- whisper
- organizations-integrating-whisper-into-customer-service-systems
- openai
- companies-using-whisper
- whisper-users
Alleged Developers
- openai
Harmed Parties
- users-whose-speech-is-misinterpreted-by-whisper
- professionals-relying-on-accurate-transcriptions
- individuals-with-speech-impairments
- general-public
- people-with-disabilities
Classification
Risk Domain
Discrimination & ToxicityRisk Subdomain
1.3. Unequal performance across groups
MIT Risk Profile
Topics
Source
Related Incidents (Discrimination & Toxicity)
View all →Research Papers on This Topic
View all →Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Explaining Explanations: An Overview of Interpretability of Machine Learning
RISE: Randomized Input Sampling for Explanation of Black-box Models
Mitigation Tools
Tools related to this risk domain, via shared responsible AI topics.
Open Source
View all →AIF360
Trusted-AI/AIF360
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
⭐ 2,872
fairlearn
fairlearn/fairlearn
A Python package to assess and improve fairness of machine learning models.
⭐ 2,199
responsible-ai-toolbox
microsoft/responsible-ai-toolbox
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.