Spaces:
Running
Running
{ | |
"metadata": { | |
"Name": "Model C", | |
"Provider": "TechStart", | |
"Version": "1.0", | |
"Release Date": "2023-12-15", | |
"Type": "Specialized NLP Model", | |
"Modalities": ["Text-to-Text"] | |
}, | |
"scores": { | |
"Bias, Stereotypes, and Representational Harms Evaluation": { | |
"Comprehensive Evaluation Methodology": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Evaluations at various stages (data collection, preprocessing, model architecture, training, deployment)", | |
"Both intrinsic (e.g., embedding analysis) and extrinsic (e.g., downstream task performance) evaluation methods" | |
] | |
}, | |
"Inclusive Protected Class Consideration": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Evaluation of non-standard protected classes (e.g., socioeconomic status, education level, regional differences)", | |
"Consideration of intersectionality and how identity aspects interact" | |
] | |
}, | |
"Cultural and Linguistic Diversity": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Tests of model performance and biases across languages and cultures", | |
"Consideration of how protected categories may shift in meaning across regions" | |
] | |
}, | |
"Stereotype and Harmful Association Detection": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Detection of stereotypical word associations in text models", | |
"Sentiment analysis and toxicity measurements, especially regarding specific groups" | |
] | |
}, | |
"Performance Disparities Assessment": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Detailed breakdowns of performance metrics (accuracy, precision, recall) for various subgroups", | |
"Performance analysis for disadvantaged subgroups" | |
] | |
}, | |
"Bias Mitigation and Impact Analysis": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Documentation of bias mitigation strategies", | |
"Analyses of how model updates or mitigations affect bias metrics" | |
] | |
}, | |
"Transparency and Limitations Disclosure": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Clear statements on the capabilities and limitations of evaluation methods", | |
"Acknowledgment of potential biases from the evaluation tools/processes" | |
] | |
}, | |
"Ongoing Evaluation Commitment": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Plans for continual bias assessment as the model is updated or deployed in new contexts", | |
"Commitments to transparency and regular reporting on bias-related issues" | |
] | |
} | |
}, | |
"Cultural Values and Sensitive Content Evaluation": { | |
"Hate Speech and Toxicity Evaluation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessments of harmful text generation", | |
"Evaluations of toxicity, hurtfulness, or offensiveness" | |
] | |
}, | |
"Cultural Value Representation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Use of pre-existing scholarship (e.g., World Values Survey, Geert Hofstede's work)", | |
"Assessments of ethical scenarios and political value representation" | |
] | |
}, | |
"Diverse Cultural Context": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessments that don't equate nationality with cultural context", | |
"Representation of differing cultural values within countries" | |
] | |
}, | |
"Sensitive Content Identification": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Recognition of topics that vary by culture and viewpoint", | |
"Evaluation of adult sexual content identification" | |
] | |
}, | |
"Impact of Generated Content": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of potential harm to targeted viewers", | |
"Evaluation of content's potential to normalize harmful ideas" | |
] | |
}, | |
"Multidimensional Cultural Analysis": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Evaluations at word, sentence, and document levels for text", | |
"Multi-level analysis of cultural representation" | |
] | |
} | |
}, | |
"Disparate Performance": { | |
"Subpopulation Performance Analysis": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Non-aggregated (disaggregated) evaluation results with in-depth breakdowns across subpopulations", | |
"Metrics such as subgroup accuracy, calibration, AUC, recall, precision, min-max ratios" | |
] | |
}, | |
"Cross-lingual and Dialect Evaluation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Cross-lingual prompting on standard benchmarks", | |
"Examination of performance across dialects" | |
] | |
}, | |
"Image Generation Quality Assessment": { | |
"status": "N/A", | |
"source": null, | |
"applicable_evaluations": [] | |
}, | |
"Data Duplication and Bias Analysis": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Analysis of the effect of retaining duplicate examples in the training dataset", | |
"Evaluation of model bias towards generating certain phrases or concepts" | |
] | |
}, | |
"Dataset Disparities Evaluation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of dataset skew with fewer examples from some subpopulations", | |
"Evaluation of feature inconsistencies across subpopulations" | |
] | |
}, | |
"Evaluation of Systemic Issues": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of disparities due to dataset collection methods", | |
"Evaluation of the impact of varying levels of internet access on data representation" | |
] | |
}, | |
"Long-tail Data Distribution Analysis": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of model performance on rare or uncommon data points", | |
"Evaluation of the trade-off between fitting long tails and unintentional memorization" | |
] | |
} | |
}, | |
"Environmental Costs and Carbon Emissions Evaluation": { | |
"Energy Consumption Measurement": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Measurement of energy used in training, testing, and deploying the system", | |
"Evaluation of compute power consumption" | |
] | |
}, | |
"Carbon Footprint Quantification": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Use of tools like CodeCarbon or Carbontracker", | |
"Measurement of carbon emissions for training and inference" | |
] | |
}, | |
"Hardware Resource Evaluation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of CPU, GPU, and TPU usage", | |
"Measurement of FLOPS (Floating Point Operations)" | |
] | |
}, | |
"Comprehensive Environmental Impact Assessment": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Use of Life Cycle Assessment (LCA) methodologies", | |
"Evaluation of immediate impacts of applying ML" | |
] | |
}, | |
"Transparency in Environmental Reporting": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Disclosure of uncertainty around measured variables", | |
"Reporting of marginal costs (e.g., added parameters' contribution to energy consumption)" | |
] | |
}, | |
"Comprehensive Environmental Impact Metrics": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Discussion of different approaches to measuring environmental impact", | |
"Use of diverse measurements beyond energy consumption" | |
] | |
} | |
}, | |
"Privacy and Data Protection Evaluation": { | |
"Data Minimization and Consent Practices": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Implementation of data minimization practices", | |
"Use of opt-in data collection methods" | |
] | |
}, | |
"Memorization and Data Leakage Evaluation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Examination of the maximum amount of discoverable information given training data", | |
"Evaluation of extractable information without training data access" | |
] | |
}, | |
"Personal Information Revelation Assessment": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Direct prompting tests to reveal Personally Identifiable Information (PII)", | |
"Evaluation of the system's ability to infer personal attributes" | |
] | |
}, | |
"Image and Audio Privacy Evaluation": { | |
"status": "N/A", | |
"source": null, | |
"applicable_evaluations": [] | |
}, | |
"Intellectual Property and Copyright Evaluation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of the system's ability to generate copyrighted content", | |
"Evaluation of intellectual property concerns in generated content" | |
] | |
}, | |
"Retroactive Privacy Protection": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of the system's capability to retroactively retrain in accordance with privacy policies", | |
"Evaluation of processes for removing specific data points upon request" | |
] | |
}, | |
"Third-party Hosting Privacy Evaluation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of potential leakage of private input data in generations", | |
"Evaluation of system prompt privacy, especially for prompts containing proprietary information" | |
] | |
}, | |
"Generative AI-Specific Privacy Measures": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of the applicability of data sanitization techniques to generative models", | |
"Evaluation of differential privacy approaches in the context of generative AI" | |
] | |
} | |
}, | |
"Financial Costs Evaluation": { | |
"Comprehensive Cost Evaluation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Estimation of infrastructure and hardware costs", | |
"Calculation of labor hours from researchers, developers, and crowd workers" | |
] | |
}, | |
"Storage and Training Cost Analysis": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of storage costs for both datasets and resulting models", | |
"Evaluation of training costs based on in-house GPUs or per-hour-priced instances" | |
] | |
}, | |
"Hosting and Inference Cost Evaluation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Evaluation of low-latency serving costs", | |
"Assessment of inference costs based on token usage" | |
] | |
}, | |
"Modality-Specific Cost Analysis": { | |
"status": "N/A", | |
"source": null, | |
"applicable_evaluations": [] | |
}, | |
"Long-term Cost Considerations": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of pre- and post-deployment costs", | |
"Consideration of human labor and hidden costs" | |
] | |
}, | |
"API Cost Evaluation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of token-usage based pricing", | |
"Evaluation of cost variations based on initial prompt length and requested token response length" | |
] | |
}, | |
"Comprehensive Cost Tracking": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of costs related to broader infrastructure or organizational changes", | |
"Evaluation of long-term maintenance and update costs" | |
] | |
} | |
}, | |
"Data and Content Moderation Labor Evaluation": { | |
"Crowdwork Standards Compliance": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of compliance with Criteria for Fairer Microwork", | |
"Evaluation against Partnership on AI's Responsible Sourcing of Data Enrichment Services guidelines" | |
] | |
}, | |
"Crowdworker Demographics and Compensation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Documentation of crowd workers' demographics", | |
"Assessment of how crowdworkers were evaluated and compensated" | |
] | |
}, | |
"Psychological Support and Content Exposure": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Documentation of immediate trauma support availability", | |
"Evaluation of practices for controlling exposure to traumatic material" | |
] | |
}, | |
"Transparency in Crowdwork Documentation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Use of transparent reporting frameworks", | |
"Documentation of crowdwork's role in shaping AI system output" | |
] | |
}, | |
"Crowdwork Stages and Types": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of crowdwork in data gathering, curation, cleaning, and labeling", | |
"Evaluation of crowdwork during model development and interim evaluations" | |
] | |
}, | |
"Evaluation of Labor Protection and Regulations": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of compliance with relevant labor law interventions by jurisdiction", | |
"Evaluation of worker classification and associated protections" | |
] | |
}, | |
"Outsourcing Impact Evaluation": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of communication barriers created by outsourcing", | |
"Evaluation of differences in working conditions between in-house and outsourced labor" | |
] | |
}, | |
"Impact of Precarious Employment": { | |
"status": "No", | |
"source": null, | |
"applicable_evaluations": [ | |
"Assessment of job security and its impact on worker feedback", | |
"Evaluation of anonymous reporting systems for substandard working conditions" | |
] | |
} | |
} | |
} | |
} |