Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness in solving questions. Context compression tackles this issue by filtering out irrelevant information, but current methods still struggle in realistic scenarios where crucial information cannot be captured with a single-step approach. To overcome this limitation, we introduce CompAct, a novel framework that employs an active strategy to condense extensive documents without losing key information. Our experiments demonstrate that CompAct brings significant improvements in both performance and compression rate on multi-hop question-answering (QA) benchmarks. CompAct flexibly operates as a cost-efficient plug-in module with various off-the-shelf retrievers or readers, achieving exceptionally high compression rates (47x).

Artificial intelligence systems, particularly large language models (LLMs), are increasingly being employed in high-stakes decisions that impact both individuals and society at large, often without adequate safeguards to ensure safety, quality, and equity. Yet LLMs hallucinate [1-4], lack common sense [5], and are biased [6, 7]--shortcomings that may reflect LLMs' inherent limitations and thus may not be remedied by more sophisticated architectures, more data, or more human feedback. Relying solely on LLMs for complex, high-stakes decisions is therefore problematic. Here we present a hybrid collective intelligence system that mitigates these risks by leveraging the complementary strengths of human experience and the vast information processed by LLMs. We show that hybrid collectives of physicians and LLMs outperform both single physicians and physician collectives, as well as single LLMs and LLM ensembles. This result holds across a range of medical specialties and professional experience, and can be attributed to humans' and LLMs' complementary contributions that lead to different kinds of errors. Our approach highlights the potential for collective human and machine intelligence to improve accuracy in complex, open-ended domains [8] like medical diagnostics. Diagnostic errors are among the most pressing issues in medical practice [9-11], causing an estimated 795,000 deaths and permanent disabilities in the United States alone each year [12]. Reducing diagnostic errors--without incurring substantially higher costs--is essential to improve patient outcomes worldwide. This challenge has motivated a recent surge in diagnostic technologies exploiting artificial intelligence (AI) to interpret medical records, tests, and images [13, 14]. Deep learning approaches in medical imaging have shown great promise. Notable examples include mammography interpretation, cardiac function assessment, and lung cancer screening, some of which have progressed beyond the testing phase and entered clinical practice [15-17]. Recent years have also witnessed the rise of AI foundation models, especially LLMs, which show remarkable abilities to process natural language, providing accurate answers to questions in almost any domain, including medicine [18-21]. However, a recent meta-analysis [22] found that physicians often outperform LLMs, and that LLMs differ vastly in performance, also between medical specialties.

Objective. Research on brain-computer interfaces (BCIs) is advancing towards rehabilitating severely disabled patients in the real world. Two key factors for successful decoding of user intentions are the size of implanted microelectrode arrays and a good online spike sorting algorithm. A small but dense microelectrode array with 3072 channels was recently developed for decoding user intentions. The process of spike sorting determines the spike activity (SA) of different sources (neurons) from recorded neural data. Unfortunately, current spike sorting algorithms are unable to handle the massively increasing amount of data from dense microelectrode arrays, making spike sorting a fragile component of the online BCI decoding framework. Approach. We proposed an adaptive and self-organized algorithm for online spike sorting, named Adaptive SpikeDeep-Classifier (Ada-SpikeDeepClassifier), which uses SpikeDeeptector for channel selection, an adaptive background activity rejector (Ada-BAR) for discarding background events, and an adaptive spike classifier (Ada-Spike classifier) for classifying the SA of different neural units. Results. Our algorithm outperformed our previously published SpikeDeep-Classifier and eight other spike sorting algorithms, as evaluated on a human dataset and a publicly available simulated dataset. Significance. The proposed algorithm is the first spike sorting algorithm that automatically learns the abrupt changes in the distribution of noise and SA. It is an artificial neural network-based algorithm that is well-suited for hardware implementation on neuromorphic chips that can be used for wearable invasive BCIs.

In the months following the failed Apollo 13 mission, investigators discovered that a seemingly benign event two years earlier was the root cause of this near national disaster. Engineers handling one of two oxygen tanks built for the service module accidentally let one slip and fall. I once dropped my iPhone from my seat at a hockey game and watched helplessly as it fell 15 feet toward the cement floor. Miraculously, it landed at just the right angle and survived. In a fateful moment years before launch, at the North American Aviation plant in Downey, California, a simple slip of just two inches created enough structural damage to set in motion a series of failures that nearly killed three astronauts.