We introduce EXIT, an extractive context compression framework that enhances both the effectiveness and efficiency of retrieval-augmented generation (RAG) in question answering (QA). Current RAG systems often struggle when retrieval models fail to rank the most relevant documents, leading to the inclusion of more context at the expense of latency and accuracy. While abstractive compression methods can drastically reduce token counts, their token-by-token generation process significantly increases end-to-end latency. Conversely, existing extractive methods reduce latency but rely on independent, non-adaptive sentence selection, failing to fully utilize contextual information. EXIT addresses these limitations by classifying sentences from retrieved documents - while preserving their contextual dependencies - enabling parallelizable, context-aware extraction that adapts to query complexity and retrieval quality. Our evaluations on both single-hop and multi-hop QA tasks show that EXIT consistently surpasses existing compression methods and even uncompressed baselines in QA accuracy, while also delivering substantial reductions in inference time and token count. By improving both effectiveness and efficiency, EXIT provides a promising direction for developing scalable, high-quality QA solutions in RAG pipelines. Our code is available at https://github.com/ThisIsHwang/EXIT

Large language models (LLMs) are trained from vast repositories of text authored by millions of distinct authors, reflecting an enormous diversity of human traits. While these models bear the potential to be used as approximations of human subjects in behavioral studies, prior efforts have been limited in steering model responses to match individual human users. In this work, we introduce "Anthology", a method for conditioning LLMs to particular virtual personas by harnessing open-ended life narratives, which we refer to as "backstories." We show that our methodology enhances the consistency and reliability of experimental outcomes while ensuring better representation of diverse sub-populations. Across three nationally representative human surveys conducted as part of Pew Research Center's American Trends Panel (ATP), we demonstrate that Anthology achieves up to 18% improvement in matching the response distributions of human respondents and 27% improvement in consistency metrics. Our code and generated backstories are available at https://github.com/CannyLab/anthology.

"Lone Star College has always been known as a leader in training tomorrow's workforce with cutting edge technology," said Dwight L. Smith, III, Ed.D., LSC vice chancellor, Academic and Workforce Success. "This collaboration with Intel will ensure our students are prepared to become the next-generation employee." A survey conducted by EdScoop found that among eight areas of IT instruction, 53% of higher education officials anticipated AI would account for the greatest increase in instructional demand over the next three years, trailing only cybersecurity studies by a small margin.

While vehicular sensor networks (VSNs) have earned the stature of a mobile sensing paradigm utilizing sensors built into cars, they have limited sensing scopes since car drivers only opportunistically discover new events. Conversely, social sensing is emerging as a new sensing paradigm where measurements about the physical world are collected from humans. In contrast to VSNs, social sensing is more pervasive, but one of its key limitations lies in its inconsistent reliability stemming from the data contributed by unreliable human sensors. In this paper, we present DASC, a road Damage-Aware Social-media-driven Car sensing framework that exploits the collective power of social sensing and VSNs for reliable disaster response applications. However, integrating VSNs with social sensing introduces a new set of challenges: i) How to leverage noisy and unreliable social signals to route the vehicles to accurate regions of interest? ii) How to tackle the inconsistent availability (e.g., churns) caused by car drivers being rational actors? iii) How to efficiently guide the cars to the event locations with little prior knowledge of the road damage caused by the disaster, while also handling the dynamics of the physical world and social media? The DASC framework addresses the above challenges by establishing a novel hybrid social-car sensing system that employs techniques from game theory, feedback control, and Markov Decision Process (MDP). In particular, DASC distills signals emitted from social media and discovers the road damages to effectively drive cars to target areas for verifying emergency events. We implement and evaluate DASC in a reputed vehicle simulator that can emulate real-world disaster response scenarios. The results of a real-world application demonstrate the superiority of DASC over current VSNs-based solutions in detection accuracy and efficiency.

The events of this year have some Mother Jones readers turning to books for perspective and comfort. Leonard Jay Hastings of Manchester, Michigan, picked up The Plot Against America and tells us this book about a dictatorship "reminds the reader that the corrective measures lie with the citizen public and not primarily with our present elected officials." Others like Emily Wilkinson in Pasadena, Texas, have immersed themselves in other worlds. Emily says The Hitchhiker's Guide to the Galaxy "provided a welcome escape from reality." We asked you to tell us which books helped get you through 2017.

On lengths of yarn stretched between chairs, sixth-grade math students were placing small yellow squares of paper, making number lines--including everything from fractions to negative decimals--in a classroom at Walsh Middle School. Their teacher, Michele O'Connor, had assigned the number lines in previous years, but this year was different. She, personally, hadn't spent much time leading students through practice problems or introducing the basic math concepts they would use in the project. That had largely been relegated to online math lessons, part of separate periods of learning time when students were free to work through computer-based lessons in any subject they chose, at their own pace. The change at Walsh, located in Framingham, Massachusetts, is part of a nationwide pilot program, one that could indicate just how deeply and how quickly the personalized-learning trend will penetrate the average classroom. Indeed, despite the buzz around personalized learning, there's no simple recipe for success, and the common ingredients -- such as adaptive-learning technology and student control over learning -- can backfire if poorly implemented. A looming question is whether personalized learning that works in, say, a tight-knit, mission-driven charter school can be reliably translated into traditional district schools with many more students, less flexible schedules, keener standardized-test worries and cultures steeped in established ways of teaching and learning.