Large language models~(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity. To assess the model performance, a typical approach is to construct evaluation benchmarks for measuring the ability level of LLMs in different aspects. Despite that a number of high-quality benchmarks have been released, the concerns about the appropriate use of these benchmarks and the fair comparison of different models are increasingly growing. Considering these concerns, in this paper, we discuss the potential risk and impact of inappropriately using evaluation benchmarks and misleadingly interpreting the evaluation results. Specially, we focus on a special issue that would lead to inappropriate evaluation, \ie \emph{benchmark leakage}, referring that the data related to evaluation sets is occasionally used for model training. This phenomenon now becomes more common since pre-training data is often prepared ahead of model test. We conduct extensive experiments to study the effect of benchmark leverage, and find that it can dramatically boost the evaluation results, which would finally lead to an unreliable assessment of model performance. To improve the use of existing evaluation benchmarks, we finally present several guidelines for both LLM developers and benchmark maintainers. We hope this work can draw attention to appropriate training and evaluation of LLMs.

With the rapid development of artificial intelligence, large language models (LLMs) have shown promising capabilities in mimicking human-level language comprehension and reasoning. This has sparked significant interest in applying LLMs to enhance various aspects of healthcare, ranging from medical education to clinical decision support. However, medicine involves multifaceted data modalities and nuanced reasoning skills, presenting challenges for integrating LLMs. This paper provides a comprehensive review on the applications and implications of LLMs in medicine. It begins by examining the fundamental applications of general-purpose and specialized LLMs, demonstrating their utilities in knowledge retrieval, research support, clinical workflow automation, and diagnostic assistance. Recognizing the inherent multimodality of medicine, the review then focuses on multimodal LLMs, investigating their ability to process diverse data types like medical imaging and EHRs to augment diagnostic accuracy. To address LLMs' limitations regarding personalization and complex clinical reasoning, the paper explores the emerging development of LLM-powered autonomous agents for healthcare. Furthermore, it summarizes the evaluation methodologies for assessing LLMs' reliability and safety in medical contexts. Overall, this review offers an extensive analysis on the transformative potential of LLMs in modern medicine. It also highlights the pivotal need for continuous optimizations and ethical oversight before these models can be effectively integrated into clinical practice. Visit https://github.com/mingze-yuan/Awesome-LLM-Healthcare for an accompanying GitHub repository containing latest papers.

A mobile ad hoc network is made up of a number of wireless portable nodes that spontaneously come together en route for establish a transitory network with no need for any central management. A mobile ad hoc network (MANET) is made up of a sizable and reasonably dense community of mobile nodes that travel across any terrain and rely solely on wireless interfaces for communication, not on any well before centralized management. Furthermore, routing be supposed to offer a method for instantly delivering data across a network between any two nodes. Finding the best packet routing from across infrastructure is the major issue, though. The proposed protocol's major goal is to identify the least-expensive nominal capacity acquisition that assures the transportation of realistic transport that ensures its durability in the event of any node failure. This study suggests the Optimized Route Selection via Red Imported Fire Ants (RIFA) Strategy as a way to improve on-demand source routing systems. Predicting Route Failure and energy Utilization is used to pick the path during the routing phase. Proposed work assess the results of the comparisons based on performance parameters like as energy usage, packet delivery rate (PDR), and end-to-end (E2E) delay. The outcome demonstrates that the proposed strategy is preferable and increases network lifetime while lowering node energy consumption and typical E2E delay under the majority of network performance measures and factors.

Smart glasses are rapidly gaining advanced functionality thanks to cutting-edge computing technologies, accelerated hardware architectures, and tiny AI algorithms. Integrating AI into smart glasses featuring a small form factor and limited battery capacity is still challenging when targeting full-day usage for a satisfactory user experience. This paper illustrates the design and implementation of tiny machine-learning algorithms exploiting novel low-power processors to enable prolonged continuous operation in smart glasses. We explore the energy- and latency-efficient of smart glasses in the case of real-time object detection. To this goal, we designed a smart glasses prototype as a research platform featuring two microcontrollers, including a novel milliwatt-power RISC-V parallel processor with a hardware accelerator for visual AI, and a Bluetooth low-power module for communication. The smart glasses integrate power cycling mechanisms, including image and audio sensing interfaces. Furthermore, we developed a family of novel tiny deep-learning models based on YOLO with sub-million parameters customized for microcontroller-based inference dubbed TinyissimoYOLO v1.3, v5, and v8, aiming at benchmarking object detection with smart glasses for energy and latency. Evaluations on the prototype of the smart glasses demonstrate TinyissimoYOLO's 17ms inference latency and 1.59mJ energy consumption per inference while ensuring acceptable detection accuracy. Further evaluation reveals an end-to-end latency from image capturing to the algorithm's prediction of 56ms or equivalently 18 fps, with a total power consumption of 62.9mW, equivalent to a 9.3 hours of continuous run time on a 154mAh battery. These results outperform MCUNet (TinyNAS+TinyEngine), which runs a simpler task (image classification) at just 7.3 fps per second.

Prompt Engineering (PE) has emerged as a critical technique for guiding Large Language Models (LLMs) in solving intricate tasks. Its importance is highlighted by its potential to significantly enhance the efficiency and effectiveness of human-machine interaction. As tasks grow increasingly complex, recent advanced PE methods have extended beyond the limitations of single-round interactions to embrace multi-round interactions, which allows for a deeper and more nuanced engagement with LLMs. In this paper, we propose an optimal control framework tailored for multi-round interactions with LLMs. This framework provides a unified mathematical structure that not only systematizes the existing PE methods but also sets the stage for rigorous analytical improvements. Furthermore, we extend this framework to include PE via ensemble methods and multi-agent collaboration, thereby enlarging the scope of applicability. By adopting an optimal control perspective, we offer fresh insights into existing PE methods and highlight theoretical challenges that warrant future research. Besides, our work lays a foundation for the development of more effective and interpretable PE methods.

Logical reasoning is fundamental for humans yet presents a substantial challenge in the domain of Artificial Intelligence. Initially, researchers used Knowledge Representation and Reasoning (KR) systems that did not scale and required non trivial manual effort. Recently, the emergence of large language models (LLMs) has demonstrated the ability to overcome various limitations of formal Knowledge Representation (KR) systems. Consequently, there is a growing interest in using LLMs for logical reasoning via natural language. This work strives to understand the proficiency of LLMs in logical reasoning by offering a brief review of the latest progress in this area; with a focus on the logical reasoning datasets, tasks, and the methods adopted to utilize LLMs for reasoning. To offer a thorough analysis, we have compiled a benchmark titled LogiGLUE. This includes 24 varied datasets encompassing deductive, abductive, and inductive reasoning. We have standardized these datasets into Seq2Seq tasks to facilitate straightforward training and evaluation for future research. Utilizing LogiGLUE as a foundation, we have trained an instruction fine tuned language model, resulting in LogiT5. We study single task training, multi task training, and a chain of thought knowledge distillation fine tuning technique to assess the performance of model across the different logical reasoning categories. By this comprehensive process, we aim to shed light on the capabilities and potential pathways for enhancing logical reasoning proficiency in LLMs, paving the way for more advanced and nuanced developments in this critical field.

Mukund Srinath (left on photo) and Pranav Venkit (right). In their paper The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis, Pranav Venkit and Mukund Srinath, and co-authors Sanjana Gautam, Saranya Venkatraman, Vipul Gupta, Rebecca J. Passonneau and Shomir Wilson, present a review of the sociotechnical aspects of sentiment analysis. In this interview, Pranav and Mukund tell us more about sentiment analysis, how they went about surveying the literature, and recommendations for researchers in the field. Sentiment analysis, often referred to as opinion mining, is a branch of natural language processing (NLP) that focuses on determining and extracting the emotional tone or sentiment expressed in text data, such as reviews, social media posts, or any written content. This is the cumulative brief definition that is most commonly used in NLP.

Multi-step stock index forecasting is vital in finance for informed decision-making. Current forecasting methods on this task frequently produce unsatisfactory results due to the inherent data randomness and instability, thereby underscoring the demand for advanced forecasting models. Given the superiority of capsule network (CapsNet) over CNN in various forecasting and classification tasks, this study investigates the potential of integrating a 1D CapsNet with an LSTM network for multi-step stock index forecasting. To this end, a hybrid 1D-CapsNet-LSTM model is introduced, which utilizes a 1D CapsNet to generate high-level capsules from sequential data and a LSTM network to capture temporal dependencies. To maintain stochastic dependencies over different forecasting horizons, a multi-input multi-output (MIMO) strategy is employed. The model's performance is evaluated on real-world stock market indices, including S&P 500, DJIA, IXIC, and NYSE, and compared to baseline models, including LSTM, RNN, and CNN-LSTM, using metrics such as RMSE, MAE, MAPE, and TIC. The proposed 1D-CapsNet-LSTM model consistently outperforms baseline models in two key aspects. It exhibits significant reductions in forecasting errors compared to baseline models. Furthermore, it displays a slower rate of error increase with lengthening forecast horizons, indicating increased robustness for multi-step forecasting tasks.

Successfully handling context is essential for any dialog understanding task. This context maybe be conversational (relying on previous user queries or system responses), visual (relying on what the user sees, for example, on their screen), or background (based on signals such as a ringing alarm or playing music). In this work, we present an overview of MARRS, or Multimodal Reference Resolution System, an on-device framework within a Natural Language Understanding system, responsible for handling conversational, visual and background context. In particular, we present different machine learning models to enable handing contextual queries; specifically, one to enable reference resolution, and one to handle context via query rewriting. We also describe how these models complement each other to form a unified, coherent, lightweight system that can understand context while preserving user privacy.

Data science has been described as the fourth paradigm for scientific discovery. The latest wave of data science research, pertaining to machine learning and artificial intelligence (AI), is growing exponentially and garnering millions of annual citations. However, this growth has been accompanied by a diminishing emphasis on social good challenges - our analysis reveals that the proportion of data science research focusing on social good is less than it has ever been. At the same time, the proliferation of machine learning and generative AI have sparked debates about the socio-technical prospects and challenges associated with data science for human flourishing, organizations, and society. Against this backdrop, we present a framework for "data science for social good" (DSSG) research that considers the interplay between relevant data science research genres, social good challenges, and different levels of socio-technical abstraction. We perform an analysis of the literature to empirically demonstrate the paucity of work on DSSG in information systems (and other related disciplines) and highlight current impediments. We then use our proposed framework to introduce the articles appearing in the special issue. We hope that this article and the special issue will spur future DSSG research and help reverse the alarming trend across data science research over the past 30-plus years in which social good challenges are garnering proportionately less attention with each passing day.