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.

Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1) scaling the number of tasks, (2) scaling the model size, and (3) finetuning on chain-of-thought data. We find that instruction finetuning with the above aspects dramatically improves performance on a variety of model classes (PaLM, T5, U-PaLM), prompting setups (zero-shot, few-shot, CoT), and evaluation benchmarks (MMLU, BBH, TyDiQA, MGSM, open-ended generation). For instance, Flan-PaLM 540B instruction-finetuned on 1.8K tasks outperforms PALM 540B by a large margin (+9.4% on average). Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints, which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but the quality bar for medical and clinical applications is high. Today, attempts to assess models' clinical knowledge typically rely on automated evaluations on limited benchmarks. There is no standard to evaluate model predictions and reasoning across a breadth of tasks. To address this, we present MultiMedQA, a benchmark combining six existing open question answering datasets spanning professional medical exams, research, and consumer queries; and HealthSearchQA, a new free-response dataset of medical questions searched online. We propose a framework for human evaluation of model answers along multiple axes including factuality, precision, possible harm, and bias. In addition, we evaluate PaLM (a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM, on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA, MedMCQA, PubMedQA, MMLU clinical topics), including 67.6% accuracy on MedQA (US Medical License Exam questions), surpassing prior state-of-the-art by over 17%. However, human evaluation reveals key gaps in Flan-PaLM responses. To resolve this we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, recall of knowledge, and medical reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal important limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLM models for clinical applications.

大型语言模型会产生类似人类的文本，这些文本推动了越来越多的应用。但是，最近的文献以及越来越多的现实世界观察表明，这些模型可以产生有毒，有偏见，不真实或其他有害的语言。尽管正在进行评估语言模型危害的工作，但要远见卓识转换出可能出现的危害可能会引起严格的基准。为了促进这种翻译，我们概述了六种表征有害文本的方式，这些方法在设计新基准时值得明确考虑。然后，我们将这些特征用作镜头来识别现有基准中的趋势和差距。最后，我们将它们应用于视角API的案例研究，这是一种毒性分类器，被广泛用于HARS基准。我们的特征提供了一块桥梁，可以在远见和有效评估之间转化。

We demonstrate that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even becoming competitive with prior state-ofthe-art fine-tuning approaches. Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous nonsparse language model, and test its performance in the few-shot setting. For all tasks, GPT-3 is applied without any gradient updates or fine-tuning, with tasks and few-shot demonstrations specified purely via text interaction with the model. GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks. We also identify some datasets where GPT-3's few-shot learning still struggles, as well as some datasets where GPT-3 faces methodological issues related to training on large web corpora.

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.

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.

本文探讨了提高语言模型的零次学习能力的简单方法。我们表明，指令调整 - 通过对说明书中所述的任务集合微调语言模型 - 大幅提升零射门上看不见任务中的表现。我们采取预训练的语言模型和指令调整它通过自然语言指令模板语言表达了60NLP任务137B参数。我们评估这种指令调整模型，我们称之为FLAN，在看不见的任务类型。FLAN显着改善其未修饰的对应的性能和超过25的20个任务，我们评估零射门175BGPT-3。FLAN甚至GPT-3通过在安利，RTE，BoolQ，AI2-ARC，OpenbookQA和StoryCloze大比分胜过几拍。消融研究显示任务和模型的规模，这个数字是指令调整取得成功的关键组成部分。

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

随着人工智能系统变得越来越强大和普遍，人们对机器的道德或缺乏道德的关注变得越来越关注。然而，向机器讲授道德是一项艰巨的任务，因为道德仍然是人类中最激烈的争论问题之一，更不用说AI了。但是，部署到数百万用户的现有AI系统已经在做出充满道德影响的决策，这构成了一个看似不可能的挑战：教学机器的道德意义，而人类继续努力努力。为了探索这一挑战，我们介绍了Delphi，这是一个基于深层神经网络的实验框架，直接训练了描述性道德判断，例如，“帮助朋友”通常是不错的，而“帮助朋友传播假新闻”不是。经验结果提供了对机器伦理的承诺和局限性的新见解。面对新的道德情况，德尔菲（Delphi）表现出强大的概括能力，而现成的神经网络模型表现出明显差的判断，包括不公正的偏见，证实了对明确教学机器的道德意义的必要性。然而，德尔菲并不完美，表现出对普遍性偏见和不一致的敏感性。尽管如此，我们还是展示了不完美的Delphi的积极用例，包括在其他不完美的AI系统中将其用作组件模型。重要的是，我们根据著名的道德理论来解释Delphi的运营化，这使我们提出了重要的未来研究问题。

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.

With the increasing ability of large language models (LLMs), in-context learning (ICL) has become a new paradigm for natural language processing (NLP), where LLMs make predictions only based on contexts augmented with a few training examples. It has been a new trend exploring ICL to evaluate and extrapolate the ability of LLMs. In this paper, we aim to survey and summarize the progress, challenges, and future work in ICL. We first present a formal definition of ICL and clarify its correlation to related studies. Then, we organize and discuss advanced techniques of ICL, including training strategies, prompting strategies, and so on. Finally, we present the challenges of ICL and provide potential directions for further research. We hope our work can encourage more research on uncovering how ICL works and improving ICL in future work.

先前的工作表明，语言模型（LMS）的大小（LMS）与它们在不同下游NLP任务上的零拍摄性能之间存在缩放定律。在这项工作中，我们表明，在用否定提示的任务评估大型LM时，这种现象并不存在，而是显示了逆缩放定律。我们对（1）验证的LMS（OPT＆GPT -3）的否定提示评估了9个不同的任务，该任务的不同尺寸（125m -175b），（2）LMS进一步预处理以推广到新颖的提示（指令），（3）提供的LMS，（3）LMS。示例很少，（4）LMS专门针对否定的提示进行了微调；所有LM类型在否定的提示上的表现较差，并在比较原始提示和否定提示的平均得分时显示人类绩效之间的巨大性能差距。通过强调现有LMS和方法的关键局限，我们敦促社区开发开发实际遵循给定指示的LMS的新方法。我们提供代码和数据集，以探索https://github.com/joeljang/negated-prompts-for-llms的否定提示。

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。

Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and reason outside of their training context, or are they simply memorizing their training corpus at finer granularity and have learnt to better understand their context? To tease apart these possibilities, we introduce ALERT, a benchmark and suite of analyses for assessing language models' reasoning ability comparing pre-trained and finetuned models on complex tasks that require reasoning skills to solve. ALERT provides a test bed to asses any language model on fine-grained reasoning skills, which spans over 20 datasets and covers 10 different reasoning skills. We leverage ALERT to further investigate the role of finetuning. With extensive empirical analysis we find that language models learn more reasoning skills such as textual entailment, abductive reasoning, and analogical reasoning during finetuning stage compared to pretraining state. We also find that when language models are finetuned they tend to overfit to the prompt template, which hurts the robustness of models causing generalization problems.

具有更多数据，计算和参数的缩放语言模型在自然语言处理方面取得了重大进展。例如，由于缩放，GPT-3能够在内心学习任务上实现强烈结果。但是，培训这些大密度模型需要大量的计算资源。在本文中，我们提出并开发了名为Glam（通用语言模型）的语言模型系列，它使用稀疏激活的专家架构来规模模型容量，同时与致密变体相比，也产生显着更少的训练成本。最大的Glam具有1.2万亿参数，比GPT-3大约为7倍。它仅消耗了用于训练GPT-3的1/3的能量，并且需要一半的计算拖鞋进行推理，同时仍然在29个NLP任务中实现更好的整体零射击和一次性性能。

Reasoning is a fundamental aspect of human intelligence that plays a crucial role in activities such as problem solving, decision making, and critical thinking. In recent years, large language models (LLMs) have made significant progress in natural language processing, and there is observation that these models may exhibit reasoning abilities when they are sufficiently large. However, it is not yet clear to what extent LLMs are capable of reasoning. This paper provides a comprehensive overview of the current state of knowledge on reasoning in LLMs, including techniques for improving and eliciting reasoning in these models, methods and benchmarks for evaluating reasoning abilities, findings and implications of previous research in this field, and suggestions on future directions. Our aim is to provide a detailed and up-to-date review of this topic and stimulate meaningful discussion and future work.

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}}.

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。

Children acquiring English make systematic errors on subject control sentences even after they have reached near-adult competence (C. Chomsky, 1969), possibly due to heuristics based on semantic roles (Maratsos, 1974). Given the advanced fluency of large generative language models, we ask whether model outputs are consistent with these heuristics, and to what degree different models are consistent with each other. We find that models can be categorized by behavior into three separate groups, with broad differences between the groups. The outputs of models in the largest group are consistent with positional heuristics that succeed on subject control but fail on object control. This result is surprising, given that object control is orders of magnitude more frequent in the text data used to train such models. We examine to what degree the models are sensitive to prompting with agent-patient information, finding that raising the salience of agent and patient relations results in significant changes in the outputs of most models. Based on this observation, we leverage an existing dataset of semantic proto-role annotations (White, et al. 2020) to explore the connections between control and labeling event participants with properties typically associated with agents and patients.