This study presents an innovative approach to the application of large language models (LLMs) in clinical decision-making, focusing on OpenAI's ChatGPT. Our approach introduces the use of contextual prompts-strategically designed to include task description, feature description, and crucially, integration of domain knowledge-for high-quality binary classification tasks even in data-scarce scenarios. The novelty of our work lies in the utilization of domain knowledge, obtained from high-performing interpretable ML models, and its seamless incorporation into prompt design. By viewing these ML models as medical experts, we extract key insights on feature importance to aid in decision-making processes. This interplay of domain knowledge and AI holds significant promise in creating a more insightful diagnostic tool. Additionally, our research explores the dynamics of zero-shot and few-shot prompt learning based on LLMs. By comparing the performance of OpenAI's ChatGPT with traditional supervised ML models in different data conditions, we aim to provide insights into the effectiveness of prompt engineering strategies under varied data availability. In essence, this paper bridges the gap between AI and healthcare, proposing a novel methodology for LLMs application in clinical decision support systems. It highlights the transformative potential of effective prompt design, domain knowledge integration, and flexible learning approaches in enhancing automated decision-making.

This study evaluates the applicability and efficiency of ChatGPT for ontology alignment using a naive approach. ChatGPT's output is compared to the results of the Ontology Alignment Evaluation Initiative 2022 campaign using conference track ontologies. This comparison is intended to provide insights into the capabilities of a conversational large language model when used in a naive way for ontology matching, and to investigate the potential advantages and disadvantages of this approach.

Large Language Models (LLMs) exhibit remarkable fluency and competence across various natural language tasks. However, recent research has highlighted their sensitivity to variations in input prompts. To deploy LLMs in a safe and reliable manner, it is crucial for their outputs to be consistent when prompted with expressions that carry the same meaning or intent. While some existing work has explored how state-of-the-art LLMs address this issue, their evaluations have been confined to assessing lexical equality of single- or multi-word answers, overlooking the consistency of generative text sequences. For a more comprehensive understanding of the consistency of LLMs in open-ended text generation scenarios, we introduce a general measure of semantic consistency, and formulate multiple versions of this metric to evaluate the performance of various LLMs. Our proposal demonstrates significantly higher consistency and stronger correlation with human evaluations of output consistency than traditional metrics based on lexical consistency. Finally, we propose a novel prompting strategy, called Ask-to-Choose (A2C), to enhance semantic consistency. When evaluated for closed-book question answering based on answer variations from the TruthfulQA benchmark, A2C increases accuracy metrics for pretrained and finetuned LLMs by up to 47%, and semantic consistency metrics for instruction-tuned models by up to 7-fold.

We introduce EgoSchema, a very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. Derived from Ego4D, EgoSchema consists of over 5000 human curated multiple choice question answer pairs, spanning over 250 hours of real video data, covering a very broad range of natural human activity and behavior. For each question, EgoSchema requires the correct answer to be selected between five given options based on a three-minute-long video clip. While some prior works have proposed video datasets with long clip lengths, we posit that merely the length of the video clip does not truly capture the temporal difficulty of the video task that is being considered. To remedy this, we introduce temporal certificate sets, a general notion for capturing the intrinsic temporal understanding length associated with a broad range of video understanding tasks & datasets. Based on this metric, we find EgoSchema to have intrinsic temporal lengths over 5.7x longer than the second closest dataset and 10x to 100x longer than any other video understanding dataset. Further, our evaluation of several current state-of-the-art video and language models shows them to be severely lacking in long-term video understanding capabilities. Even models with several billions of parameters achieve QA accuracy less than 33% (random is 20%) on the EgoSchema multi-choice question answering task, while humans achieve about 76% accuracy. We posit that \name{}{}, with its long intrinsic temporal structures and diverse complexity, would serve as a valuable evaluation probe for developing effective long-term video understanding systems in the future. Data and Zero-shot model evaluation code are open-sourced for both public and commercial use under the Ego4D license at http://egoschema.github.io

Much of the knowledge encoded in transformer language models (LMs) may be expressed in terms of relations: relations between words and their synonyms, entities and their attributes, etc. We show that, for a subset of relations, this computation is well-approximated by a single linear transformation on the subject representation. Linear relation representations may be obtained by constructing a first-order approximation to the LM from a single prompt, and they exist for a variety of factual, commonsense, and linguistic relations. However, we also identify many cases in which LM predictions capture relational knowledge accurately, but this knowledge is not linearly encoded in their representations. Our results thus reveal a simple, interpretable, but heterogeneously deployed knowledge representation strategy in transformer LMs.

We conduct a quantitative analysis contrasting human-written English news text with comparable large language model (LLM) output from 4 LLMs from the LLaMa family. Our analysis spans several measurable linguistic dimensions, including morphological, syntactic, psychometric and sociolinguistic aspects. The results reveal various measurable differences between human and AI-generated texts. Among others, human texts exhibit more scattered sentence length distributions, a distinct use of dependency and constituent types, shorter constituents, and more aggressive emotions (fear, disgust) than LLM-generated texts. LLM outputs use more numbers, symbols and auxiliaries (suggesting objective language) than human texts, as well as more pronouns. The sexist bias prevalent in human text is also expressed by LLMs.

Although rarely stated, in practice, Grammatical Error Correction (GEC) encompasses various models with distinct objectives, ranging from grammatical error detection to improving fluency. Traditional evaluation methods fail to fully capture the full range of system capabilities and objectives. Reference-based evaluations suffer from limitations in capturing the wide variety of possible correction and the biases introduced during reference creation and is prone to favor fixing local errors over overall text improvement. The emergence of large language models (LLMs) has further highlighted the shortcomings of these evaluation strategies, emphasizing the need for a paradigm shift in evaluation methodology. In the current study, we perform a comprehensive evaluation of various GEC systems using a recently published dataset of Swedish learner texts. The evaluation is performed using established evaluation metrics as well as human judges. We find that GPT-3 in a few-shot setting by far outperforms previous grammatical error correction systems for Swedish, a language comprising only 0.11% of its training data. We also found that current evaluation methods contain undesirable biases that a human evaluation is able to reveal. We suggest using human post-editing of GEC system outputs to analyze the amount of change required to reach native-level human performance on the task, and provide a dataset annotated with human post-edits and assessments of grammaticality, fluency and meaning preservation of GEC system outputs.

Multi-hop QA involves finding multiple relevant passages and step-by-step reasoning to answer complex questions. While previous approaches have developed retrieval modules for selecting relevant passages, they face challenges in scenarios beyond two hops, owing to the limited performance of one-step methods and the failure of two-step methods when selecting irrelevant passages in earlier stages. In this work, we introduce Beam Retrieval, a general end-to-end retrieval framework for multi-hop QA. This approach maintains multiple partial hypotheses of relevant passages at each step, expanding the search space and reducing the risk of missing relevant passages. Moreover, Beam Retrieval jointly optimizes an encoder and two classification heads by minimizing the combined loss across all hops. To establish a complete QA system, we incorporate a supervised reader or a zero-shot GPT-3.5. Experimental results demonstrate that Beam Retrieval achieves a nearly 50% improvement compared with baselines on challenging MuSiQue-Ans, and it also surpasses all previous retrievers on HotpotQA and 2WikiMultiHopQA. Providing high-quality context, Beam Retrieval helps our supervised reader achieve new state-of-the-art performance and substantially improves (up to 28.8 points) the QA performance of zero-shot GPT-3.5.

Upon evolving their software, organizations and individual developers have to spend a substantial effort to pay back technical debt, i.e., the fact that software is released in a shape not as good as it should be, e.g., in terms of functionality, reliability, or maintainability. This paper empirically investigates the extent to which technical debt can be automatically paid back by neural-based generative models, and in particular models exploiting different strategies for pre-training and fine-tuning. We start by extracting a dateset of 5,039 Self-Admitted Technical Debt (SATD) removals from 595 open-source projects. SATD refers to technical debt instances documented (e.g., via code comments) by developers. We use this dataset to experiment with seven different generative deep learning (DL) model configurations. Specifically, we compare transformers pre-trained and fine-tuned with different combinations of training objectives, including the fixing of generic code changes, SATD removals, and SATD-comment prompt tuning. Also, we investigate the applicability in this context of a recently-available Large Language Model (LLM)-based chat bot. Results of our study indicate that the automated repayment of SATD is a challenging task, with the best model we experimented with able to automatically fix ~2% to 8% of test instances, depending on the number of attempts it is allowed to make. Given the limited size of the fine-tuning dataset (~5k instances), the model's pre-training plays a fundamental role in boosting performance. Also, the ability to remove SATD steadily drops if the comment documenting the SATD is not provided as input to the model. Finally, we found general-purpose LLMs to not be a competitive approach for addressing SATD.

In natural language processing, transformer-based large language models (LLMs) like GPT-x models developed by OpenAI have revolutionized the landscape. Despite their impressive capabilities, these models often encounter challenges when handling tasks that differ from their training data, resulting in compromised performance. To address this, few-shot learning has emerged as a valuable technique, allowing LLMs to adapt with minimal task-specific data. One innovative strategy, known as Chain-of-Thought Prompting (CoT), has been introduced to guide LLMs in revealing cognitive processes during multi-step reasoning. In this paper, we propose Code Chain-of-Thought~(CodeCoT), which consists of two components: the Vanilla CodeCoT and the Self-exam CodeCoT. The latter incorporates self-examination, empowering the model to iteratively generate code, formulate test cases, and refine its outputs. Specifically, the process entails the generation of test examples by the model corresponding to the code it is tasked to implement. If it fails on the test examples, then it regenerates the code based on the erroneous code and associated error types. Through comprehensive experiments, we observed that both techniques significantly enhance code generation accuracy across various LLM variants. Our evaluation results reveal that CodeCoT improves the code generation effectiveness, including an unprecedented pass@1 accuracy of 79.27\% using the Self-exam CodeCoT approach on the gpt-3.5-turbo-0613 model in the HumanEval dataset.