There are a number of diverging hypotheses about the neural text degeneration problem, i.e., generating repetitive and dull loops, which makes this problem both interesting and confusing. In this work, we aim to advance our understanding by presenting a straightforward and fundamental explanation from the data perspective. Our preliminary investigation reveals a strong correlation between the degeneration issue and the presence of repetitions in training data. Subsequent experiments also demonstrate that by selectively dropping out the attention to repetitive words in training data, degeneration can be significantly minimized. Furthermore, our empirical analysis illustrates that prior works addressing the degeneration issue from various standpoints, such as the high-inflow words, the likelihood objective, and the self-reinforcement phenomenon, can be interpreted by one simple explanation. That is, penalizing the repetitions in training data is a common and fundamental factor for their effectiveness. Moreover, our experiments reveal that penalizing the repetitions in training data remains critical even when considering larger model sizes and instruction tuning.

In recent years, Large Language Models (LLMs) have witnessed a remarkable surge in prevalence, altering the landscape of natural language processing and machine learning. One key factor in improving the performance of LLMs is alignment with humans achieved with Reinforcement Learning from Human Feedback (RLHF), as for many LLMs such as GPT-4, Bard, etc. In addition, recent studies are investigating the replacement of human feedback with feedback from other LLMs named Reinforcement Learning from AI Feedback (RLAIF). We examine the biases that come along with evaluating LLMs with other LLMs and take a closer look into verbosity bias -- a bias where LLMs sometimes prefer more verbose answers even if they have similar qualities. We see that in our problem setting, GPT-4 prefers longer answers more than humans. We also propose a metric to measure this bias.

In this paper, we explore the challenges associated with navigating complex T-intersections in dense traffic scenarios for autonomous vehicles (AVs). Reinforcement learning algorithms have emerged as a promising approach to address these challenges by enabling AVs to make safe and efficient decisions in real-time. Here, we address the problem of efficiently and safely navigating T-intersections using a lower-cost, single-agent approach based on the Twin Delayed Deep Deterministic Policy Gradient (TD3) reinforcement learning algorithm. We show that our TD3-based method, when trained and tested in the CARLA simulation platform, demonstrates stable convergence and improved safety performance in various traffic densities. Our results reveal that the proposed approach enables the AV to effectively navigate T-intersections, outperforming previous methods in terms of travel delays, collision minimization, and overall cost. This study contributes to the growing body of knowledge on reinforcement learning applications in autonomous driving and highlights the potential of single-agent, cost-effective methods for addressing more complex driving scenarios and advancing reinforcement learning algorithms in the future.

Chain-of-thought reasoning, a cognitive process fundamental to human intelligence, has garnered significant attention in the realm of artificial intelligence and natural language processing. However, there still remains a lack of a comprehensive survey for this arena. To this end, we take the first step and present a thorough survey of this research field carefully and widely. We use X-of-Thought to refer to Chain-of-Thought in a broad sense. In detail, we systematically organize the current research according to the taxonomies of methods, including XoT construction, XoT structure variants, and enhanced XoT. Additionally, we describe XoT with frontier applications, covering planning, tool use, and distillation. Furthermore, we address challenges and discuss some future directions, including faithfulness, multi-modal, and theory. We hope this survey serves as a valuable resource for researchers seeking to innovate within the domain of chain-of-thought reasoning.

Historical emphasis on writing mastery has shifted with advances in generative AI, especially in scientific writing. This study analysed six AI chatbots for scholarly writing in humanities and archaeology. Using methods that assessed factual correctness and scientific contribution, ChatGPT-4 showed the highest quantitative accuracy, closely followed by ChatGPT-3.5, Bing, and Bard. However, Claude 2 and Aria scored considerably lower. Qualitatively, all AIs exhibited proficiency in merging existing knowledge, but none produced original scientific content. Inter-estingly, our findings suggest ChatGPT-4 might represent a plateau in large language model size. This research emphasizes the unique, intricate nature of human research, suggesting that AI's emulation of human originality in scientific writing is challenging. As of 2023, while AI has transformed content generation, it struggles with original contributions in humanities. This may change as AI chatbots continue to evolve into LLM-powered software.

This paper provides a summary of the 281 sorties that were flown by the 10 different models of small unmanned aerial systems (sUAS) at Hurricane Ian, and the failures made in the field. These 281 sorties, supporting 44 missions, represents the largest use of sUAS in a disaster to date (previously Hurricane Florence with 260 sorties). The sUAS operations at Hurricane Ian differ slightly from prior operations as they included the first documented uses of drones performing interior search for victims, and the first use of a VTOL fixed wing aircraft during a large scale disaster. However, there are substantive similarities to prior drone operations. Most notably, rotorcraft continue to perform the vast majority of flights, wireless data transmission capacity continues to be a limitation, and the lack of centralized control for unmanned and manned aerial systems continues to cause operational friction. This work continues by documenting the failures, both human and technological made in the field and concludes with a discussion summarizing potential areas for further work to improve sUAS response to large scale disasters.

With the continuous emergence of Chinese Large Language Models (LLMs), how to evaluate a model's capabilities has become an increasingly significant issue. The absence of a comprehensive Chinese benchmark that thoroughly assesses a model's performance, the unstandardized and incomparable prompting procedure, and the prevalent risk of contamination pose major challenges in the current evaluation of Chinese LLMs. We present CLEVA, a user-friendly platform crafted to holistically evaluate Chinese LLMs. Our platform employs a standardized workflow to assess LLMs' performance across various dimensions, regularly updating a competitive leaderboard. To alleviate contamination, CLEVA curates a significant proportion of new data and develops a sampling strategy that guarantees a unique subset for each leaderboard round. Empowered by an easy-to-use interface that requires just a few mouse clicks and a model API, users can conduct a thorough evaluation with minimal coding. Large-scale experiments featuring 23 Chinese LLMs have validated CLEVA's efficacy.

Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further align the network with the intended usage. Yet the imperfections in the proxy reward may hinder the training and lead to suboptimal results; the diversity of objectives in real-world tasks and human opinions exacerbate the issue. This paper proposes embracing the heterogeneity of diverse rewards by following a multi-policy strategy. Rather than focusing on a single a priori reward, we aim for Pareto-optimal generalization across the entire space of preferences. To this end, we propose rewarded soup, first specializing multiple networks independently (one for each proxy reward) and then interpolating their weights linearly. This succeeds empirically because we show that the weights remain linearly connected when fine-tuned on diverse rewards from a shared pre-trained initialization. We demonstrate the effectiveness of our approach for text-to-text (summarization, Q&A, helpful assistant, review), text-image (image captioning, text-to-image generation, visual grounding, VQA), and control (locomotion) tasks. We hope to enhance the alignment of deep models, and how they interact with the world in all its diversity.

Climate change is expected to aggravate wildfire activity through the exacerbation of fire weather. Improving our capabilities to anticipate wildfires on a global scale is of uttermost importance for mitigating their negative effects. In this work, we create a global fire dataset and demonstrate a prototype for predicting the presence of global burned areas on a sub-seasonal scale with the use of segmentation deep learning models. Particularly, we present an open-access global analysis-ready datacube, which contains a variety of variables related to the seasonal and sub-seasonal fire drivers (climate, vegetation, oceanic indices, human-related variables), as well as the historical burned areas and wildfire emissions for 2001-2021. We train a deep learning model, which treats global wildfire forecasting as an image segmentation task and skillfully predicts the presence of burned areas 8, 16, 32 and 64 days ahead of time. Our work motivates the use of deep learning for global burned area forecasting and paves the way towards improved anticipation of global wildfire patterns.

Soil moisture is one of the primary hydrological state (memory) variables in terrestrial systems (Dobriyal et al. 2012; Rossato et al. 2017a), and is one of the primary controls for agriculture and water management (Dobriyal et al. 2012; Rossato et al. 2017b). Soil moisture affects evapotranspiration and vegetation water availability, which are at the core of the climate-carbon cycle (Falloon et al. 2011) and play an important role in hydrological risks such as floods, drought, erosion, and landslides (Kim et al. 2019; Legates et al. 2011; Tramblay et al. 2012). Accurate measurement of soil moisture has numerous downstream benefits (Moran et al. 2015) including reduced water wastage by better understanding and managing the consumption of water (Brocca et al. 2018; Foster, Mieno, and Brozović 2020), utilising smarter irrigation methods (Kumar et al. 2014) and effective canal water management (Zafar, Prathapar, and Bastiaanssen 2021). The most accurate way to measure soil moisture is via ground-based methods such as direct gravimetric measurements (Klute 1986) or indirect methods such as dielectric reflectometry, capacitance charge, etc. (Bittelli 2011), which in-situ sensors utilize (Walker, Willgoose, and Kalma 2004). However, in-situ sensors are difficult to scale spatially, and are expensive to install and maintain.