Language models (LMs) often generate incoherent outputs: they refer to events and entity states that are incompatible with the state of the world described in their inputs. We introduce SituationSupervision, a family of approaches for improving coherence in LMs by training them to construct and condition on explicit representations of entities and their states. SituationSupervision has two components: an auxiliary situation modeling task that trains models to predict state representations in context, and a latent state inference procedure that imputes these states from partially annotated training data. SituationSupervision can be applied to both fine-tuning (by supervising LMs to encode state variables in their hidden representations) and prompting (by inducing LMs to interleave textual descriptions of entity states with output text). In both cases, SituationSupervision requires only a small number of state annotations to produce major coherence improvements (between 4-11%), showing that standard LMs can be sample-efficiently trained to model not just language but the situations it describes.

Language models (LMs) are trained on collections of documents, written by individual human agents to achieve specific goals in an outside world. During training, LMs have access only to text of these documents, with no direct evidence of the internal states of the agents that produced them -- a fact often used to argue that LMs are incapable of modeling goal-directed aspects of human language production and comprehension. Can LMs trained on text learn anything at all about the relationship between language and use? I argue that LMs are models of intentional communication in a specific, narrow sense. When performing next word prediction given a textual context, an LM can infer and represent properties of an agent likely to have produced that context. These representations can in turn influence subsequent LM generation in the same way that agents' communicative intentions influence their language. I survey findings from the recent literature showing that -- even in today's non-robust and error-prone models -- LMs infer and use representations of fine-grained communicative intentions and more abstract beliefs and goals. Despite the limited nature of their training data, they can thus serve as building blocks for systems that communicate and act intentionally.

人工推理通常可以理解为两个系统之间的相互作用：直观和关联（“系统1”）和审议和逻辑（“系统2”）。神经序列模型 - 在执行复杂，结构化任务时越来越成功 - 表现出系统1的优点和故障模式：它们是快速和学习数据的模式，但通常不一致和不连贯。在这项工作中，我们通过添加系统2-Inspired逻辑推理，寻求一种轻量级，无培训的手段来改善现有系统1样序列模型。我们探讨了该主题的几种变体，其中通过符号推理模块检查来自神经序列模型的候选几代，可以通过符号推理模块来接受或拒绝几代人。我们的方法使用神经推理来介导神经系统1和逻辑系统2.导致强大的故事生成和接地的指示，表明这种方法可以增加神经基代的一致性和准确性。

Pre-trained language models (LMs) have shown remarkable reasoning performance using explanations (or ``chain-of-thought'' (CoT)) for in-context learning. On the other hand, these reasoning tasks are usually presumed to be more approachable for symbolic programming. To make progress towards understanding in-context learning, we curate synthetic datasets containing equivalent (natural, symbolic) data pairs, where symbolic examples contain first-order logic rules and predicates from knowledge bases (KBs). Then we revisit neuro-symbolic approaches and use Language Models as Logic Programmer (LMLP) that learns from demonstrations containing logic rules and corresponding examples to iteratively reason over KBs, recovering Prolog's backward chaining algorithm. Comprehensive experiments are included to systematically compare LMLP with CoT in deductive reasoning settings, showing that LMLP enjoys more than 25% higher accuracy than CoT on length generalization benchmarks even with fewer parameters.

人类使用自然语言来撰写普通概念，将他们的环境归结为合理的日常场景描述。然而，这种生成的致辞推理（GCSR）技能缺乏最先进的文本生成方法。关于由神经文本生成模型（例如，预先接受的文本到文本变压器）生成的任意概念的描述性句子通常是语法流畅的，但可能与人类常识不相符，这主要是由于它们缺乏捕获概念关系的机制识别隐式概念，并对看不见的概念组成来执行概括的推理。在本文中，我们提出了一种想象的 - 言语（I＆V）方法，其学会在输入概念之间的关系中想象一个关系场景知识图（SKG），并在生成合理的场景描述时利用SKG作为约束。我们收集和协调来自不同领域和方式的一套知识资源，为I＆v提供丰富的辅助监督信号。该实验展示了I＆V在提高概念到句子和概念到故事的生成任务上的语言模型的有效性，同时使模型能够从更少的任务示例中学习并生成对人类注入者常识的SKG。

对事件序列的预测对于信息检索和自然语言处理中的许多现实世界应用至关重要。在事件序列预测中，未来的活动生成（FEG）是一项具有挑战性的任务，因为它不仅需要流利的文本生成，而且需要常识性推理才能保持整个事件故事的逻辑连贯性。在本文中，我们提出了一个新颖的可解释的FEG框架COEP。它突出并整合了两种类型的事件知识，对直接事件事件关系的顺序知识以及推论知识，这些知识反映了事件之间的中间角色心理学（例如意图，原因，反应），这些心理本质地将故事推向了故事。为了减轻知识遗忘问题，我们为每种类型的知识设计了两个模块，即IM和GM，它们是通过及时调整组合的。首先，IM专注于理解推论知识，以产生常识性解释并为通用汽车提供软提示向量。我们还设计了一种对比歧视器，以提高概括能力。其次，GM通过用IM的指导对直接顺序知识进行建模来生成未来事件。自动和人类评估表明，我们的方法可以产生更连贯，具体和逻辑的未来事件。

近年来带来了对自然语言理解领域的勤义代表和推理的重新兴趣。新的致辞知识图表（CSKG）的发展是这些进步的核心，因为他们的不同事实可以通过机器学习模型来解决新的和具有挑战性的任务。与此同时，由于全面地涵盖了一般勤杂朗知识所需的大规模规模，对这些资源的质量和覆盖率仍存在疑问。在这项工作中，我们将手动构建的CSKGS分配在NLP代理商遇到的所有情况下，我们将永远不会实现适用所需的覆盖范围。因此，我们提出了一种新的评估框架，用于测试KGS的效用，基于如何从中学习有效的隐式知识表示。通过这一新目标，我们提出了一个含有知识的全新CSKG的新CSKG，该知识不容易获得预用的语言模型。我们与其他领先的CSKG相比，评估其属性，表现了对勤杂朗语言知识资源的第一个大规模对研究。接下来，我们显示原子2020更适合培训知识模型，可以为新的，看不见的实体和事件产生准确，代表知识。最后，通过人类评估，我们表明，尽管使用超过430倍的参数，但GPT-3（175B参数）的几次射击性能较低，而令人印象深刻，令人印象深刻，令人印象深刻，令人印象深刻，仍然低于原子型2020的巴特的知识模型。

我们探索使用大型预用语言模型作为少量语义解析器。语义解析中的目标是给定自然语言输入的结构化含义表示。但是，培训语言模型以生成自然语言。为了弥合差距，我们使用语言模型来解释进入一个类似于英语的受控的子宫内的输入，可以自动映射到目标含义表示表示。我们的结果表明，只有少量的数据和较少的代码转换为类似英语的代表，我们为快速启动语义解析器的蓝图导致了对多个社区任务的令人惊讶的有效性能，大大超过基线方法也在相同的限制上培训数据。

Recent work has presented intriguing results examining the knowledge contained in language models (LM) by having the LM fill in the blanks of prompts such as "Obama is a by profession". These prompts are usually manually created, and quite possibly suboptimal; another prompt such as "Obama worked as a " may result in more accurately predicting the correct profession. Because of this, given an inappropriate prompt, we might fail to retrieve facts that the LM does know, and thus any given prompt only provides a lower bound estimate of the knowledge contained in an LM. In this paper, we attempt to more accurately estimate the knowledge contained in LMs by automatically discovering better prompts to use in this querying process. Specifically, we propose mining-based and paraphrasing-based methods to automatically generate high-quality and diverse prompts, as well as ensemble methods to combine answers from different prompts. Extensive experiments on the LAMA benchmark for extracting relational knowledge from LMs demonstrate that our methods can improve accuracy from 31.1% to 39.6%, providing a tighter lower bound on what LMs know. We have released the code and the resulting LM Prompt And Query Archive (LPAQA) at https://github. com/jzbjyb/LPAQA.1 Some models we use in this paper, e.g. BERT (Devlin et al., 2019), are bi-directional, and do not directly define probability distribution over text, which is the underlying definition of an LM. Nonetheless, we call them LMs for simplicity.

We address the general task of structured commonsense reasoning: given a natural language input, the goal is to generate a graph such as an event -- or a reasoning-graph. To employ large language models (LMs) for this task, existing approaches ``serialize'' the output graph as a flat list of nodes and edges. Although feasible, these serialized graphs strongly deviate from the natural language corpora that LMs were pre-trained on, hindering LMs from generating them correctly. In this paper, we show that when we instead frame structured commonsense reasoning tasks as code generation tasks, pre-trained LMs of code are better structured commonsense reasoners than LMs of natural language, even when the downstream task does not involve source code at all. We demonstrate our approach across three diverse structured commonsense reasoning tasks. In all these natural language tasks, we show that using our approach, a code generation LM (CODEX) outperforms natural-LMs that are fine-tuned on the target task (e.g., T5) and other strong LMs such as GPT-3 in the few-shot setting.

深度神经语言模型的最新进展与大规模数据集的能力相结合，加速了自然语言生成系统的发展，这些系统在多种任务和应用程序上下文中产生流利和连贯的文本（在各种成功程度上）。但是，为所需的用户控制这些模型的输出仍然是一个开放的挑战。这不仅对于自定义生成语言的内容和样式至关重要，而且对于他们在现实世界中的安全可靠部署至关重要。我们提出了一项关于受约束神经语言生成的新兴主题的广泛调查，在该主题中，我们通过区分条件和约束（后者是在输出文本上而不是输入的可检验条件），正式定义和分类自然语言生成问题，目前是可检验的）约束文本生成任务，并查看受限文本生成的现有方法和评估指标。我们的目的是强调这个新兴领域的最新进展和趋势，以告知最有希望的方向和局限性，以推动受约束神经语言生成研究的最新作品。

符号知识图（kgs）是通过昂贵的人众包或特定于域特异性的复杂信息提取管道来构建的。诸如BERT之类的新兴大型语言模型（LMS）已显示出隐式编码的大量知识，可以使用正确设计的提示来查询。但是，与明确的公斤相比，黑盒LMS中的知识通常很难访问或编辑，并且缺乏解释性。在这项工作中，我们旨在从LMS收获符号KG，这是一个由神经LMS的灵活性和可扩展性增强的自动kg构造的新框架。与通常依赖大型人类注释的数据或现有大量KG的先前作品相比，我们的方法仅需要对关系的最小定义作为输入，因此适合于以前无法提取有关丰富新关系的知识。该方法会自动生成多样化的提示，并在给定的LM内执行有效的知识搜索，以进行一致和广泛的输出。与以前的方法相比，使用我们的方法收获的知识要准确得多，如自动和人类评估所示。结果，我们源于多元化的LMS，一个新的KG家族（例如Bertnet和Robertanet），其中包含一套更丰富的常识关系，包括复杂的关系（例如，A对B的能力，但不擅长B”）人类注销的kg（例如概念网）。此外，由此产生的kg也是解释各自的源LMS的工具，从而导致对不同LMS不同知识能力的新见解。

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。

Instruction tuning enables pretrained language models to perform new tasks from inference-time natural language descriptions. These approaches rely on vast amounts of human supervision in the form of crowdsourced datasets or user interactions. In this work, we introduce Unnatural Instructions: a large dataset of creative and diverse instructions, collected with virtually no human labor. We collect 64,000 examples by prompting a language model with three seed examples of instructions and eliciting a fourth. This set is then expanded by prompting the model to rephrase each instruction, creating a total of approximately 240,000 examples of instructions, inputs, and outputs. Experiments show that despite containing a fair amount of noise, training on Unnatural Instructions rivals the effectiveness of training on open-source manually-curated datasets, surpassing the performance of models such as T0++ and Tk-Instruct across various benchmarks. These results demonstrate the potential of model-generated data as a cost-effective alternative to crowdsourcing for dataset expansion and diversification.

预审前的语言模型（LMS）易于生成具有非事实信息的文本。在这项工作中，我们测量并提高了开放式文本生成的大规模LMS的事实准确性。我们设计了FactualityPrompts测试集和指标，以衡量LM世代的事实。基于此，我们研究了参数尺寸范围从126m到530b不等的LMS的事实准确性。有趣的是，我们发现较大的LM比较小的LM更为事实，尽管先前的研究表明，在误解方面较大的LMS可能不太真实。此外，开放式文本生成中流行的采样算法（例如，顶级P）可能会损害由于每个采样步骤中引入的“均匀随机性”，因此损害了事实。我们提出的事实核采样算法会动态适应随机性，以改善发电的事实，同时保持质量。此外，我们分析了从事实文本语料库（例如Wikipedia）学习实体之间正确关联的标准培训方法的效率低下。我们提出了一种事实增强的培训方法，该方法使用topicprefix更好地意识到事实和句子完成作为培训目标，这可以大大减少事实错误。

We present Second Thought, a new learning paradigm that enables language models (LMs) to re-align with human values. By modeling the chain-of-edits between value-unaligned and value-aligned text, with LM fine-tuning and additional refinement through reinforcement learning, Second Thought not only achieves superior performance in three value alignment benchmark datasets but also shows strong human-value transfer learning ability in few-shot scenarios. The generated editing steps also offer better interpretability and ease for interactive error correction. Extensive human evaluations further confirm its effectiveness.

Many real-world applications of language models (LMs), such as code autocomplete and writing assistance, involve human-LM interaction, but the main LM benchmarks are non-interactive, where a system produces output without human intervention. To evaluate human-LM interaction, we develop a framework, Human-AI Language-based Interaction Evaluation (H-LINE), that expands non-interactive evaluation along three dimensions, capturing (i) the interactive process, not only the final output; (ii) the first-person subjective experience, not just a third-party assessment; and (iii) notions of preference beyond quality. We then design five tasks ranging from goal-oriented to open-ended to capture different forms of interaction. On four state-of-the-art LMs (three variants of OpenAI's GPT-3 and AI21's J1-Jumbo), we find that non-interactive performance does not always result in better human-LM interaction and that first-person and third-party metrics can diverge, suggesting the importance of examining the nuances of human-LM interaction.

Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions; and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, and visual-language generation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.

This paper investigates models of event implications. Specifically, how well models predict entity state-changes, by targeting their understanding of physical attributes. Nominally, Large Language models (LLM) have been exposed to procedural knowledge about how objects interact, yet our benchmarking shows they fail to reason about the world. Conversely, we also demonstrate that existing approaches often misrepresent the surprising abilities of LLMs via improper task encodings and that proper model prompting can dramatically improve performance of reported baseline results across multiple tasks. In particular, our results indicate that our prompting technique is especially useful for unseen attributes (out-of-domain) or when only limited data is available.

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.