This paper surveys the potential of contextualized AI in enhancing cyber defense capabilities, revealing significant research growth from 2015 to 2024. We identify a focus on robustness, reliability, and integration methods, while noting gaps in organizational trust and governance frameworks. Our study employs two LLM-assisted literature survey methodologies: (A) ChatGPT 4 for exploration, and (B) Gemma 2:9b for filtering with Claude 3.5 Sonnet for full-text analysis. We discuss the effectiveness and challenges of using LLMs in academic research, providing insights for future researchers.

LinkedIn is using AI and machine learning to generate screening questions for active job postings. In a paper published this week on the preprint server Arxiv.org, This isn't just theoretical research -- Job2Questions was briefly tested across millions of jobs by hiring managers and candidates on LinkedIn's platform. The timing of Job2Questions' deployment is fortuitous. Screening is a necessary evil -- a LinkedIn study found that roughly 70% of manual phone screenings uncover missing basic applicant qualifications.

At LinkedIn, we want to create economic opportunity for everyone in the global workforce. A critical aspect of this goal is matching jobs with qualified applicants. To improve hiring efficiency and reduce the need to manually screening each applicant, we develop a new product where recruiters can ask screening questions online so that they can filter qualified candidates easily. To add screening questions to all $20$M active jobs at LinkedIn, we propose a new task that aims to automatically generate screening questions for a given job posting. To solve the task of generating screening questions, we develop a two-stage deep learning model called Job2Questions, where we apply a deep learning model to detect intent from the text description, and then rank the detected intents by their importance based on other contextual features. Since this is a new product with no historical data, we employ deep transfer learning to train complex models with limited training data. We launched the screening question product and our AI models to LinkedIn users and observed significant impact in the job marketplace. During our online A/B test, we observed $+53.10\%$ screening question suggestion acceptance rate, $+22.17\%$ job coverage, $+190\%$ recruiter-applicant interaction, and $+11$ Net Promoter Score. In sum, the deployed Job2Questions model helps recruiters to find qualified applicants and job seekers to find jobs they are qualified for.

For the study, the researchers used an existing dataset (18,395) from HAPPYneuron. They examined answers to general health screening questions (addressing memory, sleep quality, medications, and medical conditions affecting thinking), demographic information, and test results from a sample of adults who took the MemTrax (M-CRT) test for episodic-memory screening. MemTrax performance and participant features were used as independent attributes: true positive/negative, percent responses/correct, response time, age, sex, and recent alcohol consumption. For predictive modeling, they used demographic information and test scores to predict binary classification of the health-related questions (yes/no) and general health status (healthy/unhealthy), based on the screening questions. "Findings from our study provide an important step in advancing the approach for clinically managing a very complex condition like Alzheimer's disease," said Michael F. Bergeron, Ph.D., senior author and senior vice president of development and applications, SIVOTEC Analytics.

Worldwide, about 44 million people are living with Alzheimer's disease or a related form of dementia. Although 82 percent of seniors in the United States say it's important to have their thinking or memory checked, only 16 percent say they receive regular cognitive assessments. Many traditional memory assessment tools are widely available to health professionals, though deficiencies in screening and detection accuracy and reliability remain prevalent. But even with increasingly available tools like MemTrax, an online memory test based on image recognition, the clinical efficacy of this approach as a memory function screening tool has not been sufficiently demonstrated or validated. In practice, there are numerous integrated and complex factors to consider in interpreting memory evaluation test results, which presents a real challenge for clinicians.

We consider the problem of group testing with sum observations and noiseless answers, in which we aim to locate multiple objects by querying the number of objects in each of a sequence of chosen sets. We study a probabilistic setting with entropy loss, in which we assume a joint Bayesian prior density on the locations of the objects and seek to choose the sets queried to minimize the expected entropy of the Bayesian posterior distribution after a fixed number of questions. We present a new non-adaptive policy, called the dyadic policy, show it is optimal among non-adaptive policies, and is within a factor of two of optimal among adaptive policies. This policy is quick to compute, its nonadaptive nature makes it easy to parallelize, and our bounds show it performs well even when compared with adaptive policies. We also study an adaptive greedy policy, which maximizes the one-step expected reduction in entropy, and show that it performs at least as well as the dyadic policy, offering greater query efficiency but reduced parallelism. Numerical experiments demonstrate that both procedures outperform a divide-and-conquer benchmark policy from the literature, called sequential bifurcation, and show how these procedures may be applied in a stylized computer vision problem.