数学推理是人类智力的核心能力，在抽象思维和逻辑推理中对机器提出了独特的挑战。最近的大型预训练的语言模型（例如GPT-3）在以文本形式（例如数学单词问题（MWP））编写的数学推理任务上取得了显着的进步。但是，未知模型是否可以处理更复杂的问题，这些问题涉及数学推理，例如表格数据。为了填补空白，我们提出了表格数学单词问题（TABMWP），这是一个包含38,431个开放域级等级问题的新数据集，这些问题需要在文本和表格数据上进行数学推理。 TABMWP中的每个问题都与表格上下文对齐，该上下文作为图像，半结构化文本和结构化表。有两种类型的问题：自由文本和多选择，每个问题都用金解决方案注释以揭示多步推理过程。我们在TABMWP上评估了不同的预训练模型，包括在几次设置中的GPT-3模型。正如先前的研究所表明的那样，由于很少有GPT-3依赖于内在的示例的选择，因此其性能是不稳定的，并且可能会降解为几乎机会。处理TABMWP等复杂问题时，不稳定的问题更为严重。为了减轻这种情况，我们进一步提出了一种新颖的方法，即PresspG，该方法利用策略梯度学习从少量培训数据中选择中文示例，然后为测试示例构造相应的提示。实验结果表明，与随机选择相比，我们的方法在准确性度量上优于最佳基线，并显着降低了预测方差，这验证了其在选择性上下文示例中的有效性。

在回答问题时，人类会利用跨不同模式可用的信息来综合一致，完整的思想链（COT）。在深度学习模型（例如大规模语言模型）的情况下，这个过程通常是黑匣子。最近，科学问题基准已用于诊断AI系统的多跳推理能力和解释性。但是，现有数据集无法为答案提供注释，或仅限于仅文本模式，小尺度和有限的域多样性。为此，我们介绍了科学问题答案（SQA），这是一个新的基准，由〜21k的多模式多种选择问题组成，其中包含各种科学主题和答案的注释，并提供相应的讲座和解释。我们进一步设计语言模型，以学习将讲座和解释作为思想链（COT），以模仿回答SQA问题时的多跳上推理过程。 SQA在语言模型中展示了COT的实用性，因为COT将问题的答案绩效提高了1.20％的GPT-3和3.99％的unifiedqa。我们还探索了模型的上限，以通过喂食输入中的那些来利用解释；我们观察到它将GPT-3的少量性能提高了18.96％。我们的分析进一步表明，与人类类似的语言模型受益于解释，从较少的数据中学习并仅使用40％的数据实现相同的性能。

Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in various fields, including science, engineering, finance, and everyday life. The development of artificial intelligence (AI) systems capable of solving math problems and proving theorems has garnered significant interest in the fields of machine learning and natural language processing. For example, mathematics serves as a testbed for aspects of reasoning that are challenging for powerful deep learning models, driving new algorithmic and modeling advances. On the other hand, recent advances in large-scale neural language models have opened up new benchmarks and opportunities to use deep learning for mathematical reasoning. In this survey paper, we review the key tasks, datasets, and methods at the intersection of mathematical reasoning and deep learning over the past decade. We also evaluate existing benchmarks and methods, and discuss future research directions in this domain.

Recently, there has been significant progress in teaching language models to perform step-by-step reasoning to solve complex numerical reasoning tasks. Chain-of-thoughts prompting (CoT) is by far the state-of-art method for these tasks. CoT uses language models to perform both reasoning and computation in the multi-step `thought' process. To disentangle computation from reasoning, we propose `Program of Thoughts' (PoT), which uses language models (mainly Codex) to express the reasoning process as a program. The computation is relegated to an external computer, which executes the generated programs to derive the answer. We evaluate PoT on five math word problem datasets (GSM, AQuA, SVAMP, TabMWP, MultiArith) and three financial-QA datasets (FinQA, ConvFinQA, TATQA) for both few-shot and zero-shot setups. Under both few-shot and zero-shot settings, PoT can show an average performance gain over CoT by around 12\% across all the evaluated datasets. By combining PoT with self-consistency decoding, we can achieve SoTA performance on all math problem datasets and near-SoTA performance on financial datasets. All of our data and code are released in Github\footnote{\url{https://github.com/wenhuchen/Program-of-Thoughts}}.

Reasoning, as an essential ability for complex problem-solving, can provide back-end support for various real-world applications, such as medical diagnosis, negotiation, etc. This paper provides a comprehensive survey of cutting-edge research on reasoning with language model prompting. We introduce research works with comparisons and summaries and provide systematic resources to help beginners. We also discuss the potential reasons for emerging such reasoning abilities and highlight future research directions.

目前用于开放域问题的最先进的生成模型（ODQA）专注于从非结构化文本信息生成直接答案。但是，大量的世界知识存储在结构化数据库中，并且需要使用SQL等查询语言访问。此外，查询语言可以回答需要复杂推理的问题，以及提供完全的解释性。在本文中，我们提出了一个混合框架，将文本和表格证据占据了输入，并根据哪种形式更好地回答这个问题而生成直接答案或SQL查询。然后可以在关联的数据库上执行生成的SQL查询以获得最终答案。据我们所知，这是第一种将Text2SQL与ODQA任务应用于ODQA任务的论文。凭经验，我们证明，在几个ODQA数据集上，混合方法始终如一地优于仅采用大边缘的均匀输入的基线模型。具体地，我们使用T5基础模型实现OpenSquad数据集的最先进的性能。在一个详细的分析中，我们证明能够生成结构的SQL查询可以始终带来增益，特别是对于那些需要复杂推理的问题。

基于知识的视觉问题答案（VQA）涉及回答图像中不存在外部知识的问题。现有方法首先从外部资源中检索知识，然后通过所选知识，输入图像和答案预测的问题进行理性。但是，这种两步方法可能导致不匹配，可能会限制VQA性能。例如，检索到的知识可能与该问题无关紧要，并且在推理过程中重新安装的知识特征可能会偏离其在知识库中的最初含义（KB）。为了应对这一挑战，我们提出了PICA，这是一种简单而有效的方法，该方法通过使用图像字幕提示GPT3用于基于知识的VQA。受GPT-3在知识检索和问题答案中的力量的启发，而不是像以前的工作那样使用结构化的KB，而是将GPT-3视为一种隐式和非结构化的KB，可以共同获取和处理相关的知识。具体来说，我们首先将图像转换为GPT-3可以理解的标题（或标签），然后通过提供一些文字中的VQA示例来调整GPT-3以几个弹射方式解决VQA任务。我们通过仔细研究进一步提高绩效：（i）哪种文本格式最能描述图像内容，以及（ii）如何更好地选择和使用中文示例。 PICA解锁了GPT-3用于多模式任务的首次使用。通过仅使用16个示例，PICA超过了OK-VQA数据集上的绝对+8.6点。我们还在VQAV2上基准了PICA，PICA还显示出不错的表现。

Open-Domain Question Answering (ODQA) requires models to answer factoid questions with no context given. The common way for this task is to train models on a large-scale annotated dataset to retrieve related documents and generate answers based on these documents. In this paper, we show that the ODQA architecture can be dramatically simplified by treating Large Language Models (LLMs) as a knowledge corpus and propose a Self-Prompting framework for LLMs to perform ODQA so as to eliminate the need for training data and external knowledge corpus. Concretely, we firstly generate multiple pseudo QA pairs with background passages and one-sentence explanations for these QAs by prompting LLMs step by step and then leverage the generated QA pairs for in-context learning. Experimental results show our method surpasses previous state-of-the-art methods by +8.8 EM averagely on three widely-used ODQA datasets, and even achieves comparable performance with several retrieval-augmented fine-tuned models.

在有问题的回答需要常识的问题上，语言模型（例如，GPT-3）已用于生成表达有助于提高性能的背景知识的文本。然而，使用此类模型的成本很高。在这项工作中，我们对较小的语言模型产生有用的中间上下文，此处称为阐述。我们的框架在更新两个语言模型之间交替使用 - 阐述生成器和一个答案预测变量 - 允许每个语言都影响彼此。我们的模型使用少于GPT-3的参数的0.5％优于具有相似尺寸的替代方案，并在四个常识性问题上回答基准测试的GPT-3上的差距缩小。人类评估表明，生成的阐述的质量很高。

大型语言模型在各种任务上显示出令人印象深刻的几次结果。但是，当知识是此类结果的关键时，就像问题回答和事实检查之类的任务一样，似乎需要存储知识的大量参数计数。众所周知，检索增强模型可以在不需要多个参数的情况下在知识密集的任务上表现出色，但是目前尚不清楚它们是否在几个弹药设置中工作。在这项工作中，我们介绍了地图集，这是一个经过精心设计和预先训练的增强语言模型，能够通过很少的培训示例学习知识密集型任务。我们对包括MMLU，苏格兰短裙和归类等各种任务进行评估，并研究文档索引内容的影响，表明它可以很容易地进行更新。值得注意的是，在自然问题上仅使用64个示例在自然问题上达到超过42 \％的准确性，尽管参数少了50倍，但比540B参数模型的表现优于540b参数模型。

最近已被证明大型语言模型在各种任务集中获得合理的零射普通化（Brown等，2020）。它已经假设这是语言模型的隐式多任务学习的结果，在语言模型中的预押（Radford等，2019）。可以通过明确的多任务学习直接引起零拍常规化？为了以缩放测试这个问题，我们开发一个系统，以便轻松地将任何自然语言任务映射到人类可读的提示表单中。我们转换一组大量的监督数据集，每个数据集都有多个提示，具有不同的措辞。这些提示的数据集允许基准测试模型执行完全看不见的任务的能力。我们介绍了一个普拉克尔编码器 - 解码器模型（Raffel等，2020; Lester等，2021），覆盖各种任务。该模型在多个标准数据集中达到强大的零点性能，通常优于其尺寸的型号超过16倍。此外，我们的方法对来自Big-替补基准测试的任务子集具有强烈性能，优于其尺寸的6倍。所有提示和培训的型号都可以在https://github.com/ bigscience-workshop / protectsource / httpsource / https：//huggingface.co/bigscience/t0pp。

Recent work has shown that fine-tuning large pre-trained language models on a collection of tasks described via instructions, a.k.a. instruction-tuning, improves their zero and few-shot generalization to unseen tasks. However, there is a limited understanding of the performance trade-offs of different decisions made during the instruction-tuning process. These decisions include the scale and diversity of the instruction-tuning benchmark, different task sampling strategies, fine-tuning with and without demonstrations, training using specialized datasets for reasoning and dialogue, and finally, the fine-tuning objectives themselves. In this paper, we characterize the effect of instruction-tuning decisions on downstream task performance when scaling both model and benchmark sizes. To this end, we create OPT-IML Bench: a large benchmark for Instruction Meta-Learning (IML) of 2000 NLP tasks consolidated into task categories from 8 existing benchmarks, and prepare an evaluation framework to measure three types of model generalizations: to tasks from fully held-out categories, to held-out tasks from seen categories, and to held-out instances from seen tasks. Through the lens of this framework, we first present insights about instruction-tuning decisions as applied to OPT-30B and further exploit these insights to train OPT-IML 30B and 175B, which are instruction-tuned versions of OPT. OPT-IML demonstrates all three generalization abilities at both scales on four different evaluation benchmarks with diverse tasks and input formats -- PromptSource, FLAN, Super-NaturalInstructions, and UnifiedSKG. Not only does it significantly outperform OPT on all benchmarks but is also highly competitive with existing models fine-tuned on each specific benchmark. We release OPT-IML at both scales, together with the OPT-IML Bench evaluation framework.

大型语言模型越来越能够通过相对较少的特定任务的监督产生流畅的出现文本。但这些模型可以准确解释分类决策吗？我们考虑使用少量人写的例子（即，以几滴方式）生成自由文本解释的任务。我们发现（1）创作更高质量的例子，以提示导致更高质量的世代; （2）令人惊讶的是，在头到头比较中，人群公司通常更喜欢GPT-3生成的解释，以众包中包含的人性写入的解释。然而，Crowdworker评级也表明，虽然模型产生了事实，语法和充分的解释，但它们具有改进的空间，例如沿着提供新颖信息和支持标签的轴。我们创建了一种管道，该管道将GPT-3与监督过滤器结合起来，该过滤器通过二进制可接受性判断来包含人类循环。尽管具有重要的主观性内在的判断可接受性，但我们的方法能够始终如一地过滤人类可接受的GPT-3生成的解释。

知识密集型任务，例如开放域问题答案（QA），需要访问大量的世界知识或领域知识。知识密集型任务的一种常见方法是采用检索到阅读的管道，该管道首先从诸如Wikipedia之类的外部语料库中检索少数相关的上下文文档，然后预测在检索文档的条件下得到答案。在本文中，我们提出了一种新的观点，可以通过用大型语言模型生成器代替文档检索器来解决知识密集型任务。我们称我们的方法生成-Read Read（GenRead），该方法首先提示大型语言模型根据给定问题生成上下文文档，然后读取生成的文档以产生最终答案。此外，我们提出了一种基于聚类的提示方法，该方法选择了不同的提示，从而产生了涵盖不同观点的生成文档，从而更好地回忆了可接受的答案。我们对三个不同的知识密集任务进行了广泛的实验，包括开放域质量检查，事实检查和对话系统。值得注意的是，GenRead在Triviaqa和WebQ上实现了71.6和54.4的精确匹配分数，显着超过了最先进的检索到+4.0和+3.9的最先进的dpr-fid，而无需从任何外部知识源中检索任何文档。最后，我们证明可以通过结合检索和生成来进一步提高模型性能。

Table-and-text hybrid question answering (HybridQA) is a widely used and challenging NLP task commonly applied in the financial and scientific domain. The early research focuses on migrating other QA task methods to HybridQA, while with further research, more and more HybridQA-specific methods have been present. With the rapid development of HybridQA, the systematic survey is still under-explored to summarize the main techniques and advance further research. So we present this work to summarize the current HybridQA benchmarks and methods, then analyze the challenges and future directions of this task. The contributions of this paper can be summarized in three folds: (1) first survey, to our best knowledge, including benchmarks, methods and challenges for HybridQA; (2) systematic investigation with the reasonable comparison of the existing systems to articulate their advantages and shortcomings; (3) detailed analysis of challenges in four important dimensions to shed light on future directions.

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.

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}.

Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the need to utilize external knowledge to assist LLMs. Unfortunately, current methods for incorporating external knowledge often require additional training or fine-tuning, which can be costly and may not be feasible for LLMs. To address this issue, we propose a novel post-processing approach, rethinking with retrieval (RR), which retrieves relevant external knowledge based on the decomposed reasoning steps obtained from the chain-of-thought (CoT) prompting. This lightweight approach does not require additional training or fine-tuning and is not limited by the input length of LLMs. We evaluate the effectiveness of RR through extensive experiments with GPT-3 on three complex reasoning tasks: commonsense reasoning, temporal reasoning, and tabular reasoning. Our results show that RR can produce more faithful explanations and improve the performance of LLMs.

大型语言模型在零拍摄设置中的许多自然语言处理（NLP）任务中表现出令人印象深刻的性能。我们询问这些模型是否展示了致辞语言 - NLP应用的关键组成部分 - 通过评估四个偶数基准的模型。我们发现大型语言模型的令人印象深刻的零射击性能主要是由于我们的基准测试中的数据集偏差。我们还表明，零拍摄性能对基准的超参数和相似性敏感到预训练数据集。此外，当在几次拍摄设置中评估模型时，我们没有观察大量改进。最后，与以前的工作相比，我们发现利用明确的致辞知识并没有产生重大改善。

预处理的大语言模型（LLM）广泛用于自然语言处理（NLP）的许多子场，通常被称为具有特定任务示例的优秀少数学习者。值得注意的是，思想链（COT）提示，这是一种通过分步答案示例引发复杂的多步推理的技术，在算术和符号推理中实现了最新的表演，难以置信的System-2任务不遵循LLMS的标准缩放定律。尽管这些成功通常归因于LLM的几次学习能力，但我们表明，LLM是通过在每个答案之前简单地添加“让我们逐步思考”而成为不错的零射击推理者。实验结果表明，使用相同的单个提示模板，我们的零射击功能明显优于零摄像机LLM在不同的基准推理任务上的零摄像机表现，包括算术（Multiarith，GSM8K，Aqua-Rat，SVAMP，SVAMP），符号推理（最后一个字母，字母，字母，字母，，，，，字母，字母）（最后一个字母），硬币翻转）和其他逻辑推理任务（日期理解，跟踪洗牌对象），而没有任何手工制作的几个示例，例如通过175B参数指令gpt模型将Multiarith的准确性从17.7％提高到78.7％，GSM8K从10.4％提高到40.7％，以及另一种现成的大型模型，540B参数Palm Palm的相似改进。在非常多样化的推理任务中，这个单一提示的多功能性暗示了LLM的尚未开发和研究的基本零拍功能，这表明可以通过简单提示来提取高级，多任务的广泛认知能力。我们希望我们的工作不仅可以作为具有挑战性的推理基准的最小零击基线，而且还强调了仔细探索和分析LLM中隐藏在LLM中的巨大的零拍知识的重要性，然后在制作Finetunning数据集或少数拍摄的典范之前。