Search for: All records

Differential privacy (DP) is applied when fine-tuning pre-trained language models (LMs) to limit leakage of training examples. While most DP research has focused on improving a model’s privacy-utility tradeoff, some find that DP can be unfair to or biased against underrepresented groups. In this work, we extensively analyze the impact of DP on bias in LMs. We find differentially private training can increase the model bias against protected groups w.r.t AUC-based bias metrics. DP makes it more difficult for the model to differentiate between the positive and negative examples from the protected groups and other groups in the rest of the population. Our results also show that the impact of DP on bias is affected by both the privacy protection level and the underlying distribution of the dataset. 

The development and measurable improvements in performance of large language models on natural language tasks opens the opportunity to utilize large language models in an educational setting to replicate human tutoring, which is often costly and inaccessible. We are particularly interested in large language models from the GPT series, created by OpenAI. In the original study we found that the quality of explanations generated with GPT-3.5 was poor, where two different approaches to generating explanations resulted in a 43% and 10% successrate. In a replication study, we were interested in whether the measurable improvements in GPT-4 performance led to a higher rate of success for generating valid explanations compared to GPT-3.5. A replication of the original study was conducted by using GPT-4 to generate explanations for the same problems given to GPT-3.5. Using GPT-4, explanation correctness dramatically improved to a success rate of 94%. We were further interested in evaluating if GPT-4 explanations were positively perceived compared to human-written explanations. A preregistered, follow-up study was implemented where 10 evaluators were asked to rate the quality of randomized GPT-4 and teacher-created explanations. Even with 4% of problems containing some amount of incorrect content, GPT-4 explanations were preferred over human explanations. 

The monitoring of data streams with a network structure have drawn increasing attention due to its wide applications in modern process control. In these applications, high-dimensional sensor nodes are interconnected with an underlying network topology. In such a case, abnormalities occurring to any node may propagate dynamically across the network and cause changes of other nodes over time. Furthermore, high dimensionality of such data significantly increased the cost of resources for data transmission and computation, such that only partial observations can be transmitted or processed in practice. Overall, how to quickly detect abnormalities in such large networks with resource constraints remains a challenge, especially due to the sampling uncertainty under the dynamic anomaly occurrences and network-based patterns. In this paper, we incorporate network structure information into the monitoring and adaptive sampling methodologies for quick anomaly detection in large networks where only partial observations are available. We develop a general monitoring and adaptive sampling method and further extend it to the case with memory constraints, both of which exploit network distance and centrality information for better process monitoring and identification of abnormalities. Theoretical investigations of the proposed methods demonstrate their sampling efficiency on balancing between exploration and exploitation, as well as the detection performance guarantee. Numerical simulations and a case study on power network have demonstrated the superiority of the proposed methods in detecting various types of shifts. Note to Practitioners —Continuous monitoring of networks for anomalous events is critical for a large number of applications involving power networks, computer networks, epidemiological surveillance, social networks, etc. This paper aims at addressing the challenges in monitoring large networks in cases where monitoring resources are limited such that only a subset of nodes in the network is observable. Specifically, we integrate network structure information of nodes for constructing sequential detection methods via effective data augmentation, and for designing adaptive sampling algorithms to observe suspicious nodes that are likely to be abnormal. Then, the method is further generalized to the case that the memory of the computation is also constrained due to the network size. The developed method is greatly beneficial and effective for various anomaly patterns, especially when the initial anomaly randomly occurs to nodes in the network. The proposed methods are demonstrated to be capable of quickly detecting changes in the network and dynamically changes the sampling priority based on online observations in various cases, as shown in the theoretical investigation, simulations and case studies. 

Abstract The recent IceCube detection of TeV neutrino emission from the nearby active galaxy NGC 1068 suggests that active galactic nuclei (AGNs) could make a sizable contribution to the diffuse flux of astrophysical neutrinos. The absence of TeVγ-rays from NGC 1068 indicates neutrino production in the vicinity of the supermassive black hole, where the high radiation density leads toγ-ray attenuation. Therefore, any potential neutrino emission from similar sources is not expected to correlate with high-energyγ-rays. Disk-corona models predict neutrino emission from Seyfert galaxies to correlate with keV X-rays because they are tracers of coronal activity. Using through-going track events from the Northern Sky recorded by IceCube between 2011 and 2021, we report results from a search for individual and aggregated neutrino signals from 27 additional Seyfert galaxies that are contained in the Swift's Burst Alert Telescope AGN Spectroscopic Survey. Besides the generic single power law, we evaluate the spectra predicted by the disk-corona model assuming stochastic acceleration parameters that match the measured flux from NGC 1068. Assuming all sources to be intrinsically similar to NGC 1068, our findings constrain the collective neutrino emission from X-ray bright Seyfert galaxies in the northern sky, but, at the same time, show excesses of neutrinos that could be associated with the objects NGC 4151 and CGCG 420-015. These excesses result in a 2.7σsignificance with respect to background expectations.