Large language models pretrained on extensive web corpora demonstrate remarkable performance across a wide range of downstream tasks. However, a growing concern is data contamination, where evaluation datasets may unintentionally be contained in the pretraining corpus, inflating model performance. Decontamination, the process of detecting and removing such data, is a potential solution; yet these contaminants may originate from altered versions of the test set, evading detection during decontamination. How different types of contamination impact the performance of language models on downstream tasks is not fully understood. We present a taxonomy that categorizes the various types of contamination encountered by LLMs during the pretraining phase and identify which types pose the highest risk. We analyze the impact of contamination on two key NLP tasks—summarization and question answering—revealing how different types of contamination influence task performance during evaluation.

Minimum Bayes Risk (MBR) decoding is a method for choosing the outputs of a machine learning system based not on the output with the highest probability, but the output with the lowest risk (expected error) among multiple candidates. It is a simple but powerful method: for an additional cost at inference time, MBR provides reliable several-point improvements across metrics for a wide variety of tasks without any additional data or training. Despite this, MBR is not frequently applied in NLP works, and knowledge of the method itself is limited. We first provide an introduction to the method and the recent literature. We show that several recent methods that do not reference MBR can be written as special cases of MBR; this reformulation provides additional theoretical justification for the performance of these methods, explaining some results that were previously only empirical. We provide theoretical and empirical results about the effectiveness of various MBR variants and make concrete recommendations for the application of MBR in NLP models, including future directions in this area.

NLP is in a period of disruptive change that is impacting our methodologies, funding sources, and public perception. In this work, we seek to understand how to shape our future by better understanding our past. We study factors that shape NLP as a field, including culture, incentives, and infrastructure by conducting long-form interviews with 26 NLP researchers of varying seniority, research area, institution, and social identity. Our interviewees identify cyclical patterns in the field, as well as new shifts without historical parallel, including changes in benchmark culture and software infrastructure. We complement this discussion with quantitative analysis of citation, authorship, and language use in the ACL Anthology over time. We conclude by discussing shared visions, concerns, and hopes for the future of NLP. We hope that this study of our field’s past and present can prompt informed discussion of our community’s implicit norms and more deliberate action to consciously shape the future.

Large language models (LLMs) enable system builders today to create competent NLP systems through prompting, where they only need to describe the task in natural language and provide a few examples. However, in other ways, LLMs are a step backward from traditional special-purpose NLP models; they require extensive computational resources for deployment and can be gated behind APIs. In this paper, we propose Prompt2Model, a general-purpose method that takes a natural language task description like the prompts provided to LLMs, and uses it to train a special-purpose model that is conducive to deployment. This is done through a multi-step process of retrieval of existing datasets and pretrained models, dataset generation using LLMs, and supervised fine-tuning on these retrieved and generated datasets. Over three tasks, we demonstrate that given the same few-shot prompt as input, Prompt2Model trains models that outperform the results of a strong LLM, gpt-3.5-turbo, by an average of 20% while being up to 700 times smaller. We also show that this data can be used to obtain reliable performance estimates of model performance, enabling model developers to assess model reliability before deployment. Prompt2Model is available open-source at https://github.com/neulab/prompt2model. Our demo video is posted at youtu.be/LYYQ_EhGd-Q.

Medical dialogue summarization is challenging due to the unstructured nature of medical conversations, the use of medical terminologyin gold summaries, and the need to identify key information across multiple symptom sets. We present a novel system for the Dialogue2Note Medical Summarization tasks in the MEDIQA 2023 Shared Task. Our approach for sectionwise summarization (Task A) is a two-stage process of selecting semantically similar dialogues and using the top-k similar dialogues as in-context examples for GPT-4. For full-note summarization (Task B), we use a similar solution with k=1. We achieved 3rd place in Task A (2nd among all teams), 4th place in Task B Division Wise Summarization (2nd among all teams), 15th place in Task A Section Header Classification (9th among all teams), and 8th place among all teams in Task B. Our results highlight the effectiveness of few-shot prompting for this task, though we also identify several weaknesses of prompting-based approaches. We compare GPT-4 performance with several finetuned baselines. We find that GPT-4 summaries are more abstractive and shorter. We make our code publicly available.

Natural language generation has witnessed significant advancements due to the training of large language models on vast internet-scale datasets. Despite these advancements, there exists a critical challenge: These models can inadvertently generate content that is toxic, inaccurate, and unhelpful, and existing automatic evaluation metrics often fall short of identifying these shortcomings. As models become more capable, human feedback is an invaluable signal for evaluating and improving models. This survey aims to provide an overview of recent research that has leveraged human feedback to improve natural language generation. First, we introduce a taxonomy distilled from existing research to categorize and organize the varied forms of feedback. Next, we discuss how feedback can be described by its format and objective, and cover the two approaches proposed to use feedback (either for training or decoding): directly using feedback or training feedback models. We also discuss existing datasets for human-feedback data collection, and concerns surrounding feedback collection. Finally, we provide an overview of the nascent field of AI feedback, which uses large language models to make judgments based on a set of principles and minimize the need for human intervention. We also release a website of this survey at feedback-gap-survey.info.

Films are a rich source of data for natural language processing. OpenSubtitles (Lison and Tiedemann, 2016) is a popular movie script dataset, used for training models for tasks such as machine translation and dialogue generation. However, movies often contain biases that reflect society at the time, and these biases may be introduced during pre-training and influence downstream models. We perform sentiment analysis on template infilling (Kurita et al., 2019) and the Sentence Embedding Association Test (May et al., 2019) to measure how BERT-based language models change after continued pre-training on OpenSubtitles. We consider gender bias as a primary motivating case for this analysis, while also measuring other social biases such as disability. We show that sentiment analysis on template infilling is not an effective measure of bias due to the rarity of disability and gender identifying tokens in the movie dialogue. We extend our analysis to a longitudinal study of bias in film dialogue over the last 110 years and find that continued pre-training on OpenSubtitles encodes additional bias into BERT. We show that BERT learns associations that reflect the biases and representation of each film era, suggesting that additional care must be taken when using historical data.

In this work, we define a new style transfer task: perspective shift, which reframes a dialouge from informal first person to a formal third person rephrasing of the text. This task requires challenging coreference resolution, emotion attribution, and interpretation of informal text. We explore several baseline approaches and discuss further directions on this task when applied to short dialogues. As a sample application, we demonstrate that applying perspective shifting to a dialogue summarization dataset (SAMSum) substantially improves the zero-shot performance of extractive news summarization models on this data. Additionally, supervised extractive models perform better when trained on perspective shifted data than on the original dialogues. We release our code publicly.

On Wikipedia, an online crowdsourced encyclopedia, volunteers enforce the encyclopedia’s editorial policies. Wikipedia’s policy on maintaining a neutral point of view has inspired recent research on bias detection, including “weasel words” and “hedges”. Yet to date, little work has been done on identifying “puffery,” phrases that are overly positive without a verifiable source. We demonstrate that collecting training data for this task requires some care, and construct a dataset by combining Wikipedia editorial annotations and information retrieval techniques. We compare several approaches to predicting puffery, and achieve 0.963 f1 score by incorporating citation features into a RoBERTa model. Finally, we demonstrate how to integrate our model with Wikipedia’s public infrastructure to give back to the Wikipedia editor community.