Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM). Existing work has combined these in simple "retrieve-then-read" pipelines in which the RM retrieves passages that are inserted into the LM prompt. To begin to fully realize the potential of frozen LMs and RMs, we propose Demonstrate-Search-Predict (DSP), a framework that relies on passing natural language texts in sophisticated pipelines between an LM and an RM. DSP can express high-level programs that bootstrap pipeline-aware demonstrations, search for relevant passages, and generate grounded predictions, systematically breaking down problems into small transformations that the LM and RM can handle more reliably. We have written novel DSP programs for answering questions in open-domain, multi-hop, and conversational settings, establishing in early evaluations new state-of-the-art in-context learning results and delivering 37-200%, 8-40%, and 80-290% relative gains against vanilla LMs, a standard retrieve-then-read pipeline, and a contemporaneous self-ask pipeline, respectively.

Neural information retrieval (IR) systems have progressed rapidly in recent years, in large part due to the release of publicly available benchmarking tasks. Unfortunately, some dimensions of this progress are illusory: the majority of the popular IR benchmarks today focus exclusively on downstream task accuracy and thus conceal the costs incurred by systems that trade away efficiency for quality. Latency, hardware cost, and other efficiency considerations are paramount to the deployment of IR systems in user-facing settings. We propose that IR benchmarks structure their evaluation methodology to include not only metrics of accuracy, but also efficiency considerations such as a query latency and the corresponding cost budget for a reproducible hardware setting. For the popular IR benchmarks MS MARCO and XOR-TyDi, we show how the best choice of IR system varies according to how these efficiency considerations are chosen and weighed. We hope that future benchmarks will adopt these guidelines toward more holistic IR evaluation.

神经信息检索（IR）具有极大的搜索和其他知识密集型语言任务。虽然许多神经IR方法将查询和文档编码为单载表示，但后期交互模型在每个令牌的粒度下产生多向量表示，并将相关性建模分解为可伸缩的令牌级计算。这种分解已被证明可以使迟到的交互更有效，但它以幅度的数量级膨胀这些模型的空间占地面积。在这项工作中，我们介绍了Colbertv2，这是一种猎犬，其与去噪的监督策略相结合的侵略性的残余压缩机制，同时提高晚期互动的质量和空间足迹。我们在各种基准中评估COLBertv2，在培训域内和外部建立最先进的质量，同时减少了晚期互动模型的空间足迹5-8 $ \ times $。

AI正在经历范式转变，随着模型的兴起（例如Bert，Dall-E，GPT-3），这些模型经过大规模的数据训练，并且可以适应广泛的下游任务。我们称这些模型基础模型来强调其至关重要但不完整的特征。该报告提供了基础模型的机会和风险的详尽说明，包括其功能（例如语言，愿景，机器人技术，推理，人类互动）和技术原则（例如，模型架构，培训程序，数据，系统，安全，安全性，评估，理论）对其应用（例如法律，医疗保健，教育）和社会影响（例如不平等，滥用，经济和环境影响，法律和道德考虑）。尽管基础模型基于标准的深度学习和转移学习，但它们的规模导致了新的新兴能力，以及它们在许多任务中的有效性都激发了同质化。同质化提供了强大的杠杆作用，但要求谨慎，因为基础模型的缺陷均由下游的所有适应模型继承。尽管即将广泛地部署基础模型，但我们目前对它们的工作方式，失败以及由于其新兴属性的影响而缺乏清晰的了解。为了解决这些问题，我们认为基础模型的许多批判性研究都需要与他们的基本社会技术性质相称。

多跳的推理（即跨两个或多个文档的推理）是NLP模型的关键要素，该模型利用大型语料库表现出广泛的知识。为了检索证据段落，多跳模型必须与整个啤酒花的快速增长的搜索空间抗衡，代表结合多个信息需求的复杂查询，并解决有关在训练段落之间跳出的最佳顺序的歧义。我们通过Baleen解决了这些问题，Baleen可以提高多跳检索的准确性，同时从多跳的训练信号中学习强大的训练信号的准确性。为了驯服搜索空间，我们提出了凝结的检索，该管道总结了每个跃点后检索到单个紧凑型上下文的管道。为了建模复杂的查询，我们引入了一个重点的后期相互作用检索器，该检索器允许同一查询表示的不同部分匹配不同的相关段落。最后，为了推断无序的训练段落中的跳跃依赖性，我们设计了潜在的跳跃订购，这是一种弱者的策略，在该策略中，受过训练的检索员本身选择了啤酒花的顺序。我们在检索中评估Baleen的两跳问答和多跳的要求验证，并确定最先进的绩效。

Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to ne-tuning deep language models (LMs) for document ranking.While remarkably e ective, the ranking models based on these LMs increase computational cost by orders of magnitude over prior approaches, particularly as they must feed each query-document pair through a massive neural network to compute a single relevance score. To tackle this, we present ColBERT, a novel ranking model that adapts deep LMs (in particular, BERT) for e cient retrieval. ColBERT introduces a late interaction architecture that independently encodes the query and the document using BERT and then employs a cheap yet powerful interaction step that models their ne-grained similarity. By delaying and yet retaining this negranular interaction, ColBERT can leverage the expressiveness of deep LMs while simultaneously gaining the ability to pre-compute document representations o ine, considerably speeding up query processing. Beyond reducing the cost of re-ranking the documents retrieved by a traditional model, ColBERT's pruning-friendly interaction mechanism enables leveraging vector-similarity indexes for end-to-end retrieval directly from a large document collection. We extensively evaluate ColBERT using two recent passage search datasets. Results show that ColBERT's e ectiveness is competitive with existing BERT-based models (and outperforms every non-BERT baseline), while executing two orders-of-magnitude faster and requiring four orders-of-magnitude fewer FLOPs per query.

Over the last decade, an approach that has gained a lot of popularity to tackle non-parametric testing problems on general (i.e., non-Euclidean) domains is based on the notion of reproducing kernel Hilbert space (RKHS) embedding of probability distributions. The main goal of our work is to understand the optimality of two-sample tests constructed based on this approach. First, we show that the popular MMD (maximum mean discrepancy) two-sample test is not optimal in terms of the separation boundary measured in Hellinger distance. Second, we propose a modification to the MMD test based on spectral regularization by taking into account the covariance information (which is not captured by the MMD test) and prove the proposed test to be minimax optimal with a smaller separation boundary than that achieved by the MMD test. Third, we propose an adaptive version of the above test which involves a data-driven strategy to choose the regularization parameter and show the adaptive test to be almost minimax optimal up to a logarithmic factor. Moreover, our results hold for the permutation variant of the test where the test threshold is chosen elegantly through the permutation of the samples. Through numerical experiments on synthetic and real-world data, we demonstrate the superior performance of the proposed test in comparison to the MMD test.

When annotators label data, a key metric for quality assurance is inter-annotator agreement (IAA): the extent to which annotators agree on their labels. Though many IAA measures exist for simple categorical and ordinal labeling tasks, relatively little work has considered more complex labeling tasks, such as structured, multi-object, and free-text annotations. Krippendorff's alpha, best known for use with simpler labeling tasks, does have a distance-based formulation with broader applicability, but little work has studied its efficacy and consistency across complex annotation tasks. We investigate the design and evaluation of IAA measures for complex annotation tasks, with evaluation spanning seven diverse tasks: image bounding boxes, image keypoints, text sequence tagging, ranked lists, free text translations, numeric vectors, and syntax trees. We identify the difficulty of interpretability and the complexity of choosing a distance function as key obstacles in applying Krippendorff's alpha generally across these tasks. We propose two novel, more interpretable measures, showing they yield more consistent IAA measures across tasks and annotation distance functions.

Generating a chain of thought (CoT) can increase large language model (LLM) performance on a wide range of tasks. Zero-shot CoT evaluations, however, have been conducted primarily on logical tasks (e.g. arithmetic, commonsense QA). In this paper, we perform a controlled evaluation of zero-shot CoT across two sensitive domains: harmful questions and stereotype benchmarks. We find that using zero-shot CoT reasoning in a prompt can significantly increase a model's likelihood to produce undesirable output. Without future advances in alignment or explicit mitigation instructions, zero-shot CoT should be avoided on tasks where models can make inferences about marginalized groups or harmful topics.

Multi-object state estimation is a fundamental problem for robotic applications where a robot must interact with other moving objects. Typically, other objects' relevant state features are not directly observable, and must instead be inferred from observations. Particle filtering can perform such inference given approximate transition and observation models. However, these models are often unknown a priori, yielding a difficult parameter estimation problem since observations jointly carry transition and observation noise. In this work, we consider learning maximum-likelihood parameters using particle methods. Recent methods addressing this problem typically differentiate through time in a particle filter, which requires workarounds to the non-differentiable resampling step, that yield biased or high variance gradient estimates. By contrast, we exploit Fisher's identity to obtain a particle-based approximation of the score function (the gradient of the log likelihood) that yields a low variance estimate while only requiring stepwise differentiation through the transition and observation models. We apply our method to real data collected from autonomous vehicles (AVs) and show that it learns better models than existing techniques and is more stable in training, yielding an effective smoother for tracking the trajectories of vehicles around an AV.