This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple (potentially long) documents. The system, called Visconde, uses a three-step pipeline to perform the task: decompose, retrieve, and aggregate. The first step decomposes the question into simpler questions using a few-shot large language model (LLM). Then, a state-of-the-art search engine is used to retrieve candidate passages from a large collection for each decomposed question. In the final step, we use the LLM in a few-shot setting to aggregate the contents of the passages into the final answer. The system is evaluated on three datasets: IIRC, Qasper, and StrategyQA. Results suggest that current retrievers are the main bottleneck and that readers are already performing at the human level as long as relevant passages are provided. The system is also shown to be more effective when the model is induced to give explanations before answering a question. Code is available at \url{https://github.com/neuralmind-ai/visconde}.

Bi-encoders and cross-encoders are widely used in many state-of-the-art retrieval pipelines. In this work we study the generalization ability of these two types of architectures on a wide range of parameter count on both in-domain and out-of-domain scenarios. We find that the number of parameters and early query-document interactions of cross-encoders play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Furthermore, we show that cross-encoders largely outperform bi-encoders of similar size in several tasks. In the BEIR benchmark, our largest cross-encoder surpasses a state-of-the-art bi-encoder by more than 4 average points. Finally, we show that using bi-encoders as first-stage retrievers provides no gains in comparison to a simpler retriever such as BM25 on out-of-domain tasks. The code is available at https://github.com/guilhermemr04/scaling-zero-shot-retrieval.git

Robust 2004是一种信息检索基准，其每个查询的大量判断使其成为可靠的评估数据集。在本文中，我们介绍了Mrobust04，这是一种多语言版本的robust04，使用Google Translate翻译为8种语言。我们还提供了该数据集上三个不同多语言检索器的结果。该数据集可在https://huggingface.co/datasets/unicamp-dl/mrobust上获得

在多语言甚至单语言中鉴定的模型的零拍跨语言能力刺激了许多假设，以解释这一有趣的经验结果。但是，由于预处理的成本，大多数研究都使用公共模型的公共模型，其预处理方法（例如代币化，语料库规模和计算预算的选择）可能会大不相同。当研究人员对自己的模型预识时，他们通常会在预算有限的情况下这样做，并且与SOTA模型相比，最终的模型的表现可能明显不足。这些实验差异导致有关这些模型跨语性能力的性质的各种不一致的结论。为了帮助对该主题进行进一步研究，我们发布了10个单语字节级模型，并在相同的配置下进行了严格审慎的概述，并具有大型计算预算（相当于V100的420天）和Corpora，比原始BERT大4倍。由于它们不含令牌，因此消除了看不见的令牌嵌入的问题，从而使研究人员可以在具有不同脚本的语言中尝试更广泛的跨语言实验。此外，我们释放了在不自然语言文本上预测的两个模型，这些模型可用于理智检查实验。关于质量检查和NLI任务的实验表明，我们的单语模型实现了多语言的竞争性能，因此可以加强我们对语言模型中跨语性可传递性的理解。

对于当前深度学习模型而言，推断出针对序列的预测的能力，即对训练示例的序列进行预测，这是一个具有挑战性的问题。最近的工作表明，这种限制仍然存在于最新的基于变压器的模型中。该问题的大多数解决方案都使用特定的体系结构或培训方法，这些方法不会推广到其他任务。我们证明，大型语言模型可以在不修改其体系结构或培训程序的情况下成功推断。实验结果表明，生成逐步的理由和引入标记令牌都是有效推断所必需的。首先，我们诱使它产生逐步的理由，然后再输出答案以有效地将任务传达给模型。但是，随着序列的更长，我们发现当前的模型难以跟踪令牌位置。为了解决这个问题，我们将输出令牌与标记令牌交织在一起，这些标记是显式位置和计数符号。我们的发现表明，这两种互补方法如何实现明显的序列外推，并突出显示当前体系结构的局限性，可以有效地推广而无需明确的表面形式指导。代码可在https://github.com/mirelleb/s.-rations-rationals-markup-tokens中获得

最近的工作表明，小型蒸馏语言模型是强大的竞争对手，这些模型是在广泛的信息检索任务中更大且较慢的数量级。由于潜伏期的限制，这使蒸馏而密集的模型是在现实世界检索应用程序中部署的首选选择。在这项工作中，我们通过证明参数和早期查询文档互动的数量在检索模型的概括能力中起着重要作用来质疑这种做法。我们的实验表明，增加模型大小会导致内域测试集的边际增长，但是在微调过程中从未见过的新领域的增长幅度更大。此外，我们表明，在几个任务中，Rerankers在很大程度上都超过了相似大小的密集。我们最大的重读者在基准-IR（BEIR）的18个数据集中的12个数据集中达到了最新技术，并超过了先前的最新水平。最后，我们确认内域的有效性不是零弹性有效性的良好指标。代码可从https://github.com/guilhermemr04/scaling-zero-shot-retrieval.git获得。

MARCO排名数据集已广泛用于培训IR任务的深度学习模型，在不同的零射击方案上实现了相当大的效果。但是，这种类型的资源是英语以外的语言的稀缺。在这项工作中，我们呈现MMARCO，MS Marco段落的多语言版本，该数据集包括使用机器翻译创建的13种语言。我们通过微调单语和多语言重新排名模型以及此数据集的密集多语言模型进行了评估。实验结果表明，在我们翻译的数据集上微调微调的多语言模型可以单独对原始英文版的模型进行微调的卓越效果。我们蒸馏的多语言RE-RANKER与非蒸馏模型具有竞争力，而参数较少的5.4倍。最后，我们展现了翻译质量和检索效果之间的正相关性，提供了证据，即翻译方法的改进可能导致多语言信息检索的改进。翻译的数据集和微调模型可在https://github.com/unicamp-dl/mmarco.git上获得。

一种有效的横向传输方法是在一种语言中微调在监督数据集上的双语或多语言模型，并以零拍方式在另一种语言上进行评估。在培训时间或推理时间翻译例子也是可行的替代方案。然而，存在与文献中很少有关的这些方法相关的成本。在这项工作中，我们在其有效性（例如，准确性），开发和部署成本方面分析交叉语言方法，以及推理时间的延迟。我们的三个任务的实验表明最好的交叉方法是高度任务依赖性的。最后，通过结合零射和翻译方法，我们在这项工作中使用的三个数据集中实现了最先进的。基于这些结果，我们对目标语言手动标记的培训数据有所了解。代码和翻译的数据集可在https://github.com/unicamp-dl/cross-lingsual-analysis上获得

This work presents a set of neural network (NN) models specifically designed for accurate and efficient fluid dynamics forecasting. In this work, we show how neural networks training can be improved by reducing data complexity through a modal decomposition technique called higher order dynamic mode decomposition (HODMD), which identifies the main structures inside flow dynamics and reconstructs the original flow using only these main structures. This reconstruction has the same number of samples and spatial dimension as the original flow, but with a less complex dynamics and preserving its main features. We also show the low computational cost required by the proposed NN models, both in their training and inference phases. The core idea of this work is to test the limits of applicability of deep learning models to data forecasting in complex fluid dynamics problems. Generalization capabilities of the models are demonstrated by using the same neural network architectures to forecast the future dynamics of four different multi-phase flows. Data sets used to train and test these deep learning models come from Direct Numerical Simulations (DNS) of these flows.

The field of robotics, and more especially humanoid robotics, has several established competitions with research oriented goals in mind. Challenging the robots in a handful of tasks, these competitions provide a way to gauge the state of the art in robotic design, as well as an indicator for how far we are from reaching human performance. The most notable competitions are RoboCup, which has the long-term goal of competing against a real human team in 2050, and the FIRA HuroCup league, in which humanoid robots have to perform tasks based on actual Olympic events. Having robots compete against humans under the same rules is a challenging goal, and, we believe that it is in the sport of archery that humanoid robots have the most potential to achieve it in the near future. In this work, we perform a first step in this direction. We present a humanoid robot that is capable of gripping, drawing and shooting a recurve bow at a target 10 meters away with considerable accuracy. Additionally, we show that it is also capable of shooting distances of over 50 meters.