Search Results for author:
Found 15 papers, 3 papers with code
To Err is AI : A Case Study Informing LLM Flaw Reporting Practices
In August of 2024, 495 hackers generated evaluations in an open-ended bug bounty targeting the Open Language Model (OLMo) from The Allen Institute for AI.
Quantifying Misalignment Between Agents: Towards a Sociotechnical Understanding of Alignment
Existing work on the alignment problem has focused mainly on (1) qualitative descriptions of the alignment problem; (2) attempting to align AI actions with human interests by focusing on value specification and learning; and/or (3) focusing on a single agent or on humanity as a monolith.
Coordinated Flaw Disclosure for AI: Beyond Security Vulnerabilities
To address this gap, we propose implementing a Coordinated Flaw Disclosure (CFD) framework tailored to the complexities of ML and AI issues.
Dual Governance: The intersection of centralized regulation and crowdsourced safety mechanisms for Generative AI
We propose a marriage of these two strategies via a framework we call Dual Governance.
Bound by the Bounty: Collaboratively Shaping Evaluation Processes for Queer AI Harms
However, these auditing processes have been criticized for their failure to integrate the knowledge of marginalized communities and consider the power dynamics between auditors and the communities.
When Fair Classification Meets Noisy Protected Attributes
Our study provides insights into the practical implications of using fair classification algorithms in scenarios where protected attributes are noisy or partially available.
Evaluating the Social Impact of Generative AI Systems in Systems and Society
Generative AI systems across modalities, ranging from text (including code), image, audio, and video, have broad social impacts, but there is no official standard for means of evaluating those impacts or for which impacts should be evaluated.
Queer In AI: A Case Study in Community-Led Participatory AI
We present Queer in AI as a case study for community-led participatory design in AI.
Can There be Art Without an Artist?
Generative AI based art has proliferated in the past year, with increasingly impressive use cases from generating fake human faces to the creation of systems that can generate thousands of artistic images from text prompts - some of these images have even been "good" enough to win accolades from qualified judges.
Subverting Fair Image Search with Generative Adversarial Perturbations
In this work we explore the intersection fairness and robustness in the context of ranking: when a ranking model has been calibrated to achieve some definition of fairness, is it possible for an external adversary to make the ranking model behave unfairly without having access to the model or training data?
FairCanary: Rapid Continuous Explainable Fairness
We incorporate QDD into a continuous model monitoring system, called FairCanary, that reuses existing explanations computed for each individual prediction to quickly compute explanations for the QDD bias metrics.
When Fair Ranking Meets Uncertain Inference
Existing fair ranking systems, especially those designed to be demographically fair, assume that accurate demographic information about individuals is available to the ranking algorithm.
Unified Shapley Framework to Explain Prediction Drift
Predictions are the currency of a machine learning model, and to understand the model's behavior over segments of a dataset, or over time, is an important problem in machine learning research and practice.
Characterizing Intersectional Group Fairness with Worst-Case Comparisons
Machine Learning or Artificial Intelligence algorithms have gained considerable scrutiny in recent times owing to their propensity towards imitating and amplifying existing prejudices in society.
Public Sphere 2.0: Targeted Commenting in Online News Media
Because the readers lack the time to go over an entire article, most of the comments are relevant to only particular sections of an article.
