Prompt tuning (PT) which only tunes the embeddings of an additional sequence of tokens per task, keeping the pre-trained language model (PLM) frozen, has shown remarkable performance in few-shot learning. Despite this, PT has been shown to rely heavily on good initialization of the prompt embeddings. In this work, we study meta prompt tuning (MPT) to systematically explore how meta-learning can help improve (if it can) cross-task generalization in PT through learning to initialize the prompt embeddings from other relevant tasks. We empirically analyze a representative set of meta learning algorithms in a wide range of adaptation settings with different source/target task configurations on a large set of few-shot tasks. With extensive experiments and analysis, we demonstrate the effectiveness of MPT. We find the improvement to be significant particularly on classification tasks. For other kinds of tasks such as question answering, we observe that while MPT can outperform PT in most cases, it does not always outperform multi-task learning. We further provide an in-depth analysis from the perspective of task similarity.
State-of-the-art neural text generation models are typically trained to maximize the likelihood of each token in the ground-truth sequence conditioned on the previous target tokens. However, during inference, the model needs to make a prediction conditioned on the tokens generated by itself. This train-test discrepancy is referred to as exposure bias. Scheduled sampling is a curriculum learning strategy that gradually exposes the model to its own predictions during training to mitigate this bias. Most of the proposed approaches design a scheduler based on training steps, which generally requires careful tuning depending on the training setup. In this work, we introduce Dynamic Scheduled Sampling with Imitation Loss (DySI), which maintains the schedule based solely on the training time accuracy, while enhancing the curriculum learning by introducing an imitation loss, which attempts to make the behavior of the decoder indistinguishable from the behavior of a teacher-forced decoder. DySI is universally applicable across training setups with minimal tuning. Extensive experiments and analysis show that DySI not only achieves notable improvements on standard machine translation benchmarks, but also significantly improves the robustness of other text generation models.
Pre-trained large language models can efficiently interpolate human-written prompts in a natural way. Multitask prompted learning can help generalization through a diverse set of tasks at once, thus enhancing the potential for more effective downstream fine-tuning. To perform efficient multitask-inference in the same batch, parameter-efficient fine-tuning methods such as prompt tuning have been proposed. However, the existing prompt tuning methods may lack generalization. We propose SPT, a semi-parametric prompt tuning method for multitask prompted learning. The novel component of SPT is a memory bank from where memory prompts are retrieved based on discrete prompts. Extensive experiments, such as (i) fine-tuning a full language model with SPT on 31 different tasks from 8 different domains and evaluating zero-shot generalization on 9 heldout datasets under 5 NLP task categories and (ii) pretraining SPT on the GLUE datasets and evaluating fine-tuning on the SuperGLUE datasets, demonstrate effectiveness of SPT.
Are large language models (LLMs) like GPT-3 psychologically safe? In this work, we design unbiased prompts to evaluate LLMs systematically from a psychological perspective. Firstly, we test the personality traits of three different LLMs with Short Dark Triad (SD-3) and Big Five Inventory (BFI). We find all of them show higher scores on SD-3 than the human average, indicating a relatively darker personality. Furthermore, LLMs like InstructGPT and FLAN-T5, which are fine-tuned with safety metrics, do not necessarily have more positive personalities. They score higher on Machiavellianism and Narcissism than GPT-3. Secondly, we test the LLMs in GPT-3 series on well-being tests to study the impact of fine-tuning with more training data. Interestingly, we observe a continuous increase in well-being scores from GPT-3 to InstructGPT. Following the observations, we show that instruction-finetune FLAN-T5 with positive answers in BFI can effectively improve the model from a psychological perspective. Finally, we call on the community to evaluate and improve LLMs' safety systematically instead of at the sentence level only.
GPT-3 (Generative Pre-trained Transformer 3) is a large-scale autoregressive language model developed by OpenAI, which has demonstrated impressive few-shot performance on a wide range of natural language processing (NLP) tasks. Hence, an intuitive application is to use it for data annotation. In this paper, we investigate whether GPT-3 can be used as a good data annotator for NLP tasks. Data annotation is the process of labeling data that could be used to train machine learning models. It is a crucial step in the development of NLP systems, as it allows the model to learn the relationship between the input data and the desired output. Given the impressive language capabilities of GPT-3, it is natural to wonder whether it can be used to effectively annotate data for NLP tasks. In this paper, we evaluate the performance of GPT-3 as a data annotator by comparing it with traditional data annotation methods and analyzing its output on a range of tasks. Through this analysis, we aim to provide insight into the potential of GPT-3 as a general-purpose data annotator in NLP.
With the rise of task-specific pre-training objectives, abstractive summarization models like PEGASUS offer appealing zero-shot performance on downstream summarization tasks. However, the performance of such unsupervised models still lags significantly behind their supervised counterparts. Similarly to the supervised setup, we notice a very high variance in quality among summary candidates from these models whereas only one candidate is kept as the summary output. In this paper, we propose to re-rank summary candidates in an unsupervised manner, aiming to close the performance gap between unsupervised and supervised models. Our approach improves the pre-trained unsupervised PEGASUS by 4.37% to 7.27% relative mean ROUGE across four widely-adopted summarization benchmarks, and achieves relative gains of 7.51% (up to 23.73%) averaged over 30 transfer setups.
Human evaluation is the foundation upon which the evaluation of both summarization systems and automatic metrics rests. However, existing human evaluation protocols and benchmarks for summarization either exhibit low inter-annotator agreement or lack the scale needed to draw statistically significant conclusions, and an in-depth analysis of human evaluation is lacking. In this work, we address the shortcomings of existing summarization evaluation along the following axes: 1) We propose a modified summarization salience protocol, Atomic Content Units (ACUs), which relies on fine-grained semantic units and allows for high inter-annotator agreement. 2) We curate the Robust Summarization Evaluation (RoSE) benchmark, a large human evaluation dataset consisting of over 22k summary-level annotations over state-of-the-art systems on three datasets. 3) We compare our ACU protocol with three other human evaluation protocols, underscoring potential confounding factors in evaluation setups. 4) We evaluate existing automatic metrics using the collected human annotations across evaluation protocols and demonstrate how our benchmark leads to more statistically stable and significant results. Furthermore, our findings have important implications for evaluating large language models (LLMs), as we show that LLMs adjusted by human feedback (e.g., GPT-3.5) may overfit unconstrained human evaluation, which is affected by the annotators' prior, input-agnostic preferences, calling for more robust, targeted evaluation methods.
Machine learning models usually assume i.i.d data during training and testing, but data and tasks in real world often change over time. To emulate the transient nature of real world, we propose a challenging but practical task: text classification in-the-wild, which introduces different non-stationary training/testing stages. Decomposing a complex task into modular components can enable robust generalisation under such non-stationary environment. However, current modular approaches in NLP do not take advantage of recent advances in parameter efficient tuning of pretrained language models. To close this gap, we propose MODULARPROMPT, a label-modular prompt tuning framework for text classification tasks. In MODULARPROMPT, the input prompt consists of a sequence of soft label prompts, each encoding modular knowledge related to the corresponding class label. In two of most formidable settings, MODULARPROMPT outperforms relevant baselines by a large margin demonstrating strong generalisation ability. We also conduct comprehensive analysis to validate whether the learned prompts satisfy properties of a modular representation.
We introduce BotSIM, a modular, open-source Bot SIMulation environment with dialog generation, user simulation and conversation analytics capabilities. BotSIM aims to serve as a one-stop solution for large-scale data-efficient end-to-end evaluation, diagnosis and remediation of commercial task-oriented dialog (TOD) systems to significantly accelerate commercial bot development and evaluation, reduce cost and time-to-market. BotSIM adopts a layered design comprising the infrastructure layer, the adaptor layer and the application layer. The infrastructure layer hosts key models and components to support BotSIM's major functionalities via a streamlined "generation-simulation-remediation" pipeline. The adaptor layer is used to extend BotSIM to accommodate new bot platforms. The application layer provides a suite of command line tools and a Web App to significantly lower the entry barrier for BotSIM users such as bot admins or practitioners. In this report, we focus on the technical designs of various system components. A detailed case study using Einstein BotBuilder is also presented to show how to apply BotSIM pipeline for bot evaluation and remediation. The detailed system descriptions can be found in our system demo paper. The toolkit is available at: https://github.com/salesforce/BotSIM .