Recent work has shown that large language models are capable of generating natural language reasoning steps or Chains-of-Thoughts (CoT) to answer a multi-step question when prompted to do so. This is insufficient, however, when the necessary knowledge is not available or up-to-date within a model's parameters. A straightforward approach to address this is to retrieve text from an external knowledge source using the question as a query and prepend it as context to the model's input. This, however, is also insufficient for multi-step QA where \textit{what to retrieve} depends on \textit{what has already been derived}. To address this issue we propose IRCoT, a new approach that interleaves retrieval with CoT for multi-step QA, guiding the retrieval with CoT and in turn using retrieved results to improve CoT. Our experiments with GPT3 show substantial improvements in retrieval (up to 22 points) and downstream QA (up to 16 points) over the baselines on four datasets: HotpotQA, 2WikiMultihopQA, MuSiQue, and IIRC. Notably, our method also works well for much smaller models such as T5-Flan-large (0.7B) without any additional training.

Knowledge about outcomes is critical for complex event understanding but is hard to acquire. We show that by pre-identifying a participant in a complex event, crowd workers are able to (1) infer the collective impact of salient events that make up the situation, (2) annotate the volitional engagement of participants in causing the situation, and (3) ground the outcome of the situation in state changes of the participants. By creating a multi-step interface and a careful quality control strategy, we collect a high quality annotated dataset of 8K short newswire narratives and ROCStories with high inter-annotator agreement (0.74-0.96 weighted Fleiss Kappa). Our dataset, POQue (Participant Outcome Questions), enables the exploration and development of models that address multiple aspects of semantic understanding. Experimentally, we show that current language models lag behind human performance in subtle ways through our task formulations that target abstract and specific comprehension of a complex event, its outcome, and a participant's influence over the event culmination.

从有限的资源中获得最大收益可以进步自然语言处理（NLP）研究和实践，同时保守资源。这些资源可能是数据，时间，存储或能源。NLP的最新工作从缩放率产生了有趣的结果。但是，仅使用比例来改善结果意味着资源消耗也会扩展。这种关系激发了对有效方法的研究，这些方法需要更少的资源才能获得相似的结果。这项调查涉及NLP效率的方法和发现，旨在指导该领域的新研究人员并激发新方法的发展。

叙事中的事件可以通过其参与者的基本状态理解为一致的整体。通常，这些参与者在叙述中没有明确提及，而是通过常识性或推论填写。理解叙述的模型应该能够推断出这些隐性参与者状态，以及有关这些状态对叙事的影响的原因。为了促进这一目标，我们介绍了一个新的众包参与者指出的数据集意大利面。该数据集包含有效的，可推断的参与者状态；对国家的反事实扰动；如果反事实是真实的，那么故事的变化将是必要的。我们介绍了三项基于州的推理任务，这些任务测试了一个故事何时由故事启用，修改一个反事实状态的故事，并解释给定经过修订的故事的最有可能的状态变化。我们的基准测试实验表明，尽管当今的LLM能够在某种程度上推理有关州的推理，但仍有很大的改进空间，这表明了未来研究的潜在途径。

Question-answering datasets require a broad set of reasoning skills. We show how to use question decompositions to teach language models these broad reasoning skills in a robust fashion. Specifically, we use widely available QDMR representations to programmatically create hard-to-cheat synthetic contexts for real questions in six multi-step reasoning datasets. These contexts are carefully designed to avoid reasoning shortcuts prevalent in real contexts that prevent models from learning the right skills. This results in a pretraining dataset, named TeaBReaC, containing 525K multi-step questions (with associated formal programs) covering about 900 reasoning patterns. We show that pretraining standard language models (LMs) on TeaBReaC before fine-tuning them on target datasets improves their performance by up to 13 F1 points across 4 multi-step QA datasets, with up to 21 point gain on more complex questions. The resulting models also demonstrate higher robustness, with a 5-8 F1 point improvement on two contrast sets. Furthermore, TeaBReaC pretraining substantially improves model performance and robustness even when starting with numerate LMs pretrained using recent methods (e.g., PReasM, POET). Our work thus shows how to effectively use decomposition-guided contexts to robustly teach multi-step reasoning.

许多自然语言处理专注于利用大容量语言模型，通常通过单个消息培训，这是预测一个或多个令牌的任务。然而，探讨了在更高层次的上下文中建模人类语言（即消息序列）。在姿态检测和其他社交媒体任务中，目标是预测消息的属性，我们具有由作者松散地连接的上下文数据。在这里，我们介绍了消息级变换器（MELT） - 通过Twitter预先培训并应用于姿态预测的任务的分层消息编码器。我们专注于立场预测，因为从知道消息的上下文中受益（即，先前消息的序列）。该模型使用屏蔽语言建模的变体培训;其中代替预测令牌，它试图通过重建损耗来生成整个掩码（聚合）消息向量。我们发现将该预训练的屏蔽消息级变压器应用于姿态检测的下游任务，实现了67％的F1性能。

Real-world autonomous missions often require rich interaction with nearby objects, such as doors or switches, along with effective navigation. However, such complex behaviors are difficult to learn because they involve both high-level planning and low-level motor control. We present a novel framework, Cascaded Compositional Residual Learning (CCRL), which learns composite skills by recursively leveraging a library of previously learned control policies. Our framework learns multiplicative policy composition, task-specific residual actions, and synthetic goal information simultaneously while freezing the prerequisite policies. We further explicitly control the style of the motion by regularizing residual actions. We show that our framework learns joint-level control policies for a diverse set of motor skills ranging from basic locomotion to complex interactive navigation, including navigating around obstacles, pushing objects, crawling under a table, pushing a door open with its leg, and holding it open while walking through it. The proposed CCRL framework leads to policies with consistent styles and lower joint torques, which we successfully transfer to a real Unitree A1 robot without any additional fine-tuning.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Artificial Intelligence (AI) and its data-centric branch of machine learning (ML) have greatly evolved over the last few decades. However, as AI is used increasingly in real world use cases, the importance of the interpretability of and accessibility to AI systems have become major research areas. The lack of interpretability of ML based systems is a major hindrance to widespread adoption of these powerful algorithms. This is due to many reasons including ethical and regulatory concerns, which have resulted in poorer adoption of ML in some areas. The recent past has seen a surge in research on interpretable ML. Generally, designing a ML system requires good domain understanding combined with expert knowledge. New techniques are emerging to improve ML accessibility through automated model design. This paper provides a review of the work done to improve interpretability and accessibility of machine learning in the context of global problems while also being relevant to developing countries. We review work under multiple levels of interpretability including scientific and mathematical interpretation, statistical interpretation and partial semantic interpretation. This review includes applications in three areas, namely food processing, agriculture and health.

Workloads in modern cloud data centers are becoming increasingly complex. The number of workloads running in cloud data centers has been growing exponentially for the last few years, and cloud service providers (CSP) have been supporting on-demand services in real-time. Realizing the growing complexity of cloud environment and cloud workloads, hardware vendors such as Intel and AMD are increasingly introducing cloud-specific workload acceleration features in their CPU platforms. These features are typically targeted towards popular and commonly-used cloud workloads. Nonetheless, uncommon, customer-specific workloads (unknown workloads), if their characteristics are different from common workloads (known workloads), may not realize the potential of the underlying platform. To address this problem of realizing the full potential of the underlying platform, we develop a machine learning based technique to characterize, profile and predict workloads running in the cloud environment. Experimental evaluation of our technique demonstrates good prediction performance. We also develop techniques to analyze the performance of the model in a standalone manner.