Related papers: Ground(less) Truth: A Causal Framework for Proxy L…
AI models, including both time-series-specific and general-purpose Foundation Models (FMs), have demonstrated strong potential in time-series forecasting across sectors like finance. However, these models are highly sensitive to input…
Noisy labels are both inevitable and problematic in machine learning methods, as they negatively impact models' generalization ability by causing overfitting. In the context of learning with noise, the transition matrix plays a crucial role…
Many decision-making processes have begun to incorporate an AI element, including prison sentence recommendations, college admissions, hiring, and mortgage approval. In all of these cases, AI models are being trained to help human decision…
Decision support systems for classification tasks are predominantly designed to predict the value of the ground truth labels. However, since their predictions are not perfect, these systems also need to make human experts understand when…
Although many fairness criteria have been proposed to ensure that machine learning algorithms do not exhibit or amplify our existing social biases, these algorithms are trained on datasets that can themselves be statistically biased. In…
Addressing bias in the trained machine learning system often requires access to sensitive attributes. In practice, these attributes are not available either due to legal and policy regulations or data unavailability for a given demographic.…
Warning: This research studies AI persuasion and bias amplification that could be misused; all experiments are for safety evaluation. Large Language Models (LLMs) now generate convincing, human-like text and are widely used in content…
Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…
We present new results for nonparametric identification of causal effects using noisy proxies for unobserved confounders. Our approach builds on the results of \citet{Hu2008} who tackle the problem of general measurement error. We call this…
Machine learning algorithms are now frequently used in sensitive contexts that substantially affect the course of human lives, such as credit lending or criminal justice. This is driven by the idea that `objective' machines base their…
Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment. This \textit{motivated reasoning} at a collective level can be detrimental to society when…
Artificial intelligence (AI) comes with great opportunities but can also pose significant risks. Automatically generated explanations for decisions can increase transparency and foster trust, especially for systems based on automated…
Machine learning models are often brittle on production data despite achieving high accuracy on benchmark datasets. Benchmark datasets have traditionally served dual purposes: first, benchmarks offer a standard on which machine learning…
Human labeled datasets, along with their corresponding evaluation algorithms, play an important role in boundary detection. We here present a psychophysical experiment that addresses the reliability of such benchmarks. To find better…
Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and…
Generative Artificial Intelligence (GenAI) is now widespread in education, yet the efficacy of GenAI systems remains constrained by the quality and interpretation of the labeled data used to train and evaluate them. Studies commonly report…
Conditioning on some set of confounders that causally affect both treatment and outcome variables can be sufficient for eliminating bias introduced by all such confounders when estimating causal effect of the treatment on the outcome from…
Objective: Firearm injury research necessitates using data from often-exploited vulnerable populations of Black and Brown Americans. In order to minimize distrust, this study provides a framework for establishing AI trust and transparency…
The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized…
The emergence of synthetic data for privacy protection, training data generation, or simply convenient access to quasi-realistic data in any shape or volume complicates the concept of ground truth. Synthetic data mimic real-world…