相关论文: Oversampling Higher-Performing Minorities During M…

This PhD thesis investigates the societal impact of machine learning (ML). ML increasingly informs consequential decisions and recommendations, significantly affecting many aspects of our lives. As these data-driven systems are often…

Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of…

Traditional scaling laws in natural language processing suggest that increasing model size and training data enhances performance. However, recent studies reveal deviations, particularly in large language models, where performance…

In model-based reinforcement learning, planning with an imperfect model of the environment has the potential to harm learning progress. But even when a model is imperfect, it may still contain information that is useful for planning. In…

When evaluating the performance of clinical machine learning models, one must consider the deployment population. When the population of patients with observed labels is only a subset of the deployment population (label selection), standard…

Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…

Data quality affects machine learning (ML) model performances, and data scientists spend considerable amount of time on data cleaning before model training. However, to date, there does not exist a rigorous study on how exactly cleaning…

Over the past decades, researchers and ML practitioners have come up with better and better ways to build, understand and improve the quality of ML models, but mostly under the key assumption that the training data is distributed…

Machine learning models are known to memorize samples from their training data, raising concerns around privacy and generalization. Counterfactual self-influence is a popular metric to study memorization, quantifying how the model's…

In many economically relevant contexts where machine learning is deployed, multiple platforms obtain data from the same pool of users, each of whom selects the platform that best serves them. Prior work in this setting focuses exclusively…

Artificial intelligence (AI) is increasingly being used for medical imaging tasks. However, there can be biases in AI models, particularly when they are trained using imbalanced training datasets. One such example has been the strong…

In this study, we conduct a resume-screening experiment (N=528) where people collaborate with simulated AI models exhibiting race-based preferences (bias) to evaluate candidates for 16 high and low status occupations. Simulated AI bias…

By planning through a learned dynamics model, model-based reinforcement learning (MBRL) offers the prospect of good performance with little environment interaction. However, it is common in practice for the learned model to be inaccurate,…

Various types of social biases have been reported with pretrained Masked Language Models (MLMs) in prior work. However, multiple underlying factors are associated with an MLM such as its model size, size of the training data, training…

Machine Learning (ML) research has increased substantially in recent years, due to the success of predictive modeling across diverse application domains. However, well-known barriers exist when attempting to deploy ML models in high-stakes,…

As LLMs are increasingly integrated into user-facing applications, addressing biases that perpetuate societal inequalities is crucial. While much work has gone into measuring or mitigating biases in these models, fewer studies have…

Generating synthetic datasets via large language models (LLMs) has emerged as a promising approach to improve LLM performance. However, LLMs inherently reflect biases in their training data, leading to a critical challenge: when models are…

Modern multilingual models are trained on concatenated text from multiple languages in hopes of conferring benefits to each (positive transfer), with the most pronounced benefits accruing to low-resource languages. However, recent work has…

Biased human decisions have consequential impacts across various domains, yielding unfair treatment of individuals and resulting in suboptimal outcomes for organizations and society. In recognition of this fact, organizations regularly…

Artificial Intelligence (AI) is increasingly used in hiring, with large language models (LLMs) having the potential to influence or even make hiring decisions. However, this raises pressing concerns about bias, fairness, and trust,…