Computation and Language (cs.CL)

Abstract: Objective: To assess the performance of the OpenAI GPT API in accurately and efficiently identifying relevant titles and abstracts from real-world clinical review datasets and compare its performance against ground truth labelling by two independent human reviewers. Methods: We introduce a novel workflow using the OpenAI GPT API for screening titles and abstracts in clinical reviews. A Python script was created to make calls to the GPT API with the screening criteria in natural language and a corpus of title and abstract datasets that have been filtered by a minimum of two human reviewers. We compared the performance of our model against human-reviewed papers across six review papers, screening over 24,000 titles and abstracts. Results: Our results show an accuracy of 0.91, a sensitivity of excluded papers of 0.91, and a sensitivity of included papers of 0.76. On a randomly selected subset of papers, the GPT API demonstrated the ability to provide reasoning for its decisions and corrected its initial decision upon being asked to explain its reasoning for a subset of incorrect classifications. Conclusion: The GPT API has the potential to streamline the clinical review process, save valuable time and effort for researchers, and contribute to the overall quality of clinical reviews. By prioritizing the workflow and acting as an aid rather than a replacement for researchers and reviewers, the GPT API can enhance efficiency and lead to more accurate and reliable conclusions in medical research.

Abstract: Most human interactions occur in the form of spoken conversations where the semantic meaning of a given utterance depends on the context. Each utterance in spoken conversation can be represented by many semantic and speaker attributes, and there has been an interest in building Spoken Language Understanding (SLU) systems for automatically predicting these attributes. Recent work has shown that incorporating dialogue history can help advance SLU performance. However, separate models are used for each SLU task, leading to an increase in inference time and computation cost. Motivated by this, we aim to ask: can we jointly model all the SLU tasks while incorporating context to facilitate low-latency and lightweight inference? To answer this, we propose a novel model architecture that learns dialog context to jointly predict the intent, dialog act, speaker role, and emotion for the spoken utterance. Note that our joint prediction is based on an autoregressive model and we need to decide the prediction order of dialog attributes, which is not trivial. To mitigate the issue, we also propose an order agnostic training method. Our experiments show that our joint model achieves similar results to task-specific classifiers and can effectively integrate dialog context to further improve the SLU performance.

Abstract: Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetuned on datasets that contain user-submitted examples, e.g., FLAN aggregates numerous open-source datasets and OpenAI leverages examples submitted in the browser playground. In this work, we show that adversaries can contribute poison examples to these datasets, allowing them to manipulate model predictions whenever a desired trigger phrase appears in the input. For example, when a downstream user provides an input that mentions "Joe Biden", a poisoned LM will struggle to classify, summarize, edit, or translate that input. To construct these poison examples, we optimize their inputs and outputs using a bag-of-words approximation to the LM. We evaluate our method on open-source instruction-tuned LMs. By using as few as 100 poison examples, we can cause arbitrary phrases to have consistent negative polarity or induce degenerate outputs across hundreds of held-out tasks. Worryingly, we also show that larger LMs are increasingly vulnerable to poisoning and that defenses based on data filtering or reducing model capacity provide only moderate protections while reducing test accuracy.

Abstract: The performance of large language models (LLMs) has recently improved to the point where the models can generate valid and coherent meta-linguistic analyses of data. This paper illustrates a vast potential for analyses of the meta-linguistic abilities of large language models. LLMs are primarily trained on language data in the form of text; analyzing their meta-linguistic abilities is informative both for our understanding of the general capabilities of LLMs as well as for models of linguistics. In this paper, we propose several types of experiments and prompt designs that allow us to analyze the ability of GPT-4 to generate meta-linguistic analyses. We focus on three linguistics subfields with formalisms that allow for a detailed analysis of GPT-4's theoretical capabilities: theoretical syntax, phonology, and semantics. We identify types of experiments, provide general guidelines, discuss limitations, and offer future directions for this research program.

Abstract: Many recent advances in natural language generation have been fueled by training large language models on internet-scale data. However, this paradigm can lead to models that generate toxic, inaccurate, and unhelpful content, and automatic evaluation metrics often fail to identify these behaviors. As models become more capable, human feedback is an invaluable signal for evaluating and improving models. This survey aims to provide an overview of the recent research that has leveraged human feedback to improve natural language generation. First, we introduce an encompassing formalization of feedback, and identify and organize existing research into a taxonomy following this formalization. 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 the 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 exploits large language models to make judgments based on a set of principles and minimize the need for human intervention.