Related papers: Detecting Compromised Implicit Association Test Re…
Semi-supervised learning approaches train on small sets of labeled data along with large sets of unlabeled data. Self-training is a semi-supervised teacher-student approach that often suffers from the problem of "confirmation bias" that…
Labeling a large set of data is expensive. Active learning aims to tackle this problem by asking to annotate only the most informative data from the unlabeled set. We propose a novel active learning approach that utilizes self-supervised…
Despite having achieved great success for sentiment analysis, existing neural models struggle with implicit sentiment analysis. This may be due to the fact that they may latch onto spurious correlations ("shortcuts", e.g., focusing only on…
During recent years, active learning has evolved into a popular paradigm for utilizing user's feedback to improve accuracy of learning algorithms. Active learning works by selecting the most informative sample among unlabeled data and…
When training powerful AI systems to perform complex tasks, it may be challenging to provide training signals which are robust to optimization. One concern is \textit{measurement tampering}, where the AI system manipulates multiple…
Classification models learn to generalize the associations between data samples and their target classes. However, researchers have increasingly observed that machine learning practice easily leads to systematic errors in AI applications, a…
Autonomous agents (robots) face tremendous challenges while interacting with heterogeneous human agents in close proximity. One of these challenges is that the autonomous agent does not have an accurate model tailored to the specific human…
Inferring causal relationships or related associations from observational data can be invalidated by the existence of hidden confounding. We focus on a high-dimensional linear regression setting, where the measured covariates are affected…
Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on…
Familiar statistical tests and estimates are obtained by the direct observation of cases of interest: a clinical trial of a new drug, for instance, will compare the drug's effects on a relevant set of patients and controls. Sometimes,…
As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequences, yet existing evaluations remain largely…
Traditional models of active learning assume a learner can directly manipulate or query a covariate $X$ in order to study its relationship with a response $Y$. However, if $X$ is a feature of a complex system, it may be possible only to…
Subjective tests are the gold standard for evaluating speech quality and intelligibility; however, they are time-consuming and expensive. Thus, objective measures that align with human perceptions are crucial. This study evaluates the…
Word embeddings are often criticized for capturing undesirable word associations such as gender stereotypes. However, methods for measuring and removing such biases remain poorly understood. We show that for any embedding model that…
Conjoint analysis is a popular experimental design used to measure multidimensional preferences. Researchers examine how varying a factor of interest, while controlling for other relevant factors, influences decision-making. Currently,…
Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…
Pragmatics, the ability to infer meaning beyond literal interpretation, is crucial for social cognition and communication. While LLMs have been benchmarked for their pragmatic understanding, improving their performance remains…
Uncertainty quantification is an important part of many performance critical applications. This paper provides a simple alternative to existing approaches such as ensemble learning and bayesian neural networks. By directly modeling the loss…
Inspired by the concept of active learning, we propose active inference$\unicode{x2013}$a methodology for statistical inference with machine-learning-assisted data collection. Assuming a budget on the number of labels that can be collected,…
Assessing image quality is crucial in image processing tasks such as compression, super-resolution, and denoising. While subjective assessments involving human evaluators provide the most accurate quality scores, they are impractical for…