Performance bugs are non-functional bugs that can even manifest in well-tested commercial products. Fixing these performance bugs is an important yet challenging problem. In this work, we address this challenge and present a new approach called Retrieval-Augmented Prompt Generation (RAPGen). Given a code snippet with a performance issue, RAPGen first retrieves a prompt instruction from a pre-constructed knowledge-base of previous performance bug fixes and then generates a prompt using the retrieved instruction. It then uses this prompt on a Large Language Model (such as Codex) in zero-shot to generate a fix. We compare our approach with the various prompt variations and state of the art methods in the task of performance bug fixing. Our evaluation shows that RAPGen can generate performance improvement suggestions equivalent or better than a developer in ~60% of the cases, getting ~39% of them verbatim, in an expert-verified dataset of past performance changes made by C# developers.

This paper presents UMASS_BioNLP team participation in the MEDIQA-Chat 2023 shared task for Task-A and Task-C. We focus especially on Task-C and propose a novel LLMs cooperation system named a doctor-patient loop to generate high-quality conversation data sets. The experiment results demonstrate that our approaches yield reasonable performance as evaluated by automatic metrics such as ROUGE, medical concept recall, BLEU, and Self-BLEU. Furthermore, we conducted a comparative analysis between our proposed method and ChatGPT and GPT-4. This analysis also investigates the potential of utilizing cooperation LLMs to generate high-quality datasets.

Large Language Models (LLMs) exhibit exceptional abilities for causal analysis between concepts in numerous societally impactful domains, including medicine, science, and law. Recent research on LLM performance in various causal discovery and inference tasks has given rise to a new ladder in the classical three-stage framework of causality. In this paper, we advance the current research of LLM-driven causal discovery by proposing a novel framework that combines knowledge-based LLM causal analysis with data-driven causal structure learning. To make LLM more than a query tool and to leverage its power in discovering natural and new laws of causality, we integrate the valuable LLM expertise on existing causal mechanisms into statistical analysis of objective data to build a novel and practical baseline for causal structure learning. We introduce a universal set of prompts designed to extract causal graphs from given variables and assess the influence of LLM prior causality on recovering causal structures from data. We demonstrate the significant enhancement of LLM expertise on the quality of recovered causal structures from data, while also identifying critical challenges and issues, along with potential approaches to address them. As a pioneering study, this paper aims to emphasize the new frontier that LLMs are opening for classical causal discovery and inference, and to encourage the widespread adoption of LLM capabilities in data-driven causal analysis.

Pre-trained large language models (PLMs) underlie most new developments in natural language processing. They have shifted the field from application-specific model pipelines to a single model that is adapted to a wide range of tasks. Autoregressive PLMs like GPT-3 or PaLM, alongside techniques like few-shot learning, have additionally shifted the output modality to generation instead of classification or regression. Despite their ubiquitous use, the generation quality of language models is rarely evaluated when these models are introduced. Additionally, it is unclear how existing generation tasks--while they can be used to compare systems at a high level--relate to the real world use cases for which people have been adopting them. In this work, we discuss how to adapt existing application-specific generation benchmarks to PLMs and provide an in-depth, empirical study of the limitations and capabilities of PLMs in natural language generation tasks along dimensions such as scale, architecture, input and output language. Our results show that PLMs differ in their applicability to different data regimes and their generalization to multiple languages and inform which PLMs to use for a given generation task setup. We share best practices to be taken into consideration when benchmarking generation capabilities during the development of upcoming PLMs.

With the rise of Large Language Models (LLMs) and their ubiquitous deployment in diverse domains, measuring language model behavior on realistic data is imperative. For example, a company deploying a client-facing chatbot must ensure that the model will not respond to client requests with profanity. Current evaluations approach this problem using small, domain-specific datasets with human-curated labels. These evaluation sets are often sampled from a narrow and simplified distribution, and data sources can unknowingly be leaked into the training set which can lead to misleading evaluations. To bypass these drawbacks, we propose a framework for self-supervised evaluation of LLMs by analyzing their sensitivity or invariance to transformations on the input text. Self-supervised evaluation can directly monitor LLM behavior on datasets collected in the wild or streamed during live model deployment. We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence, in addition to sensitivity to grammatical structure and tokenization errors. When comparisons to similar human-labeled benchmarks are available, we find strong correlations between self-supervised and human-supervised evaluations. The self-supervised paradigm complements current evaluation strategies that rely on labeled data.

Large-scale Pretrained Language Models (LLMs), such as ChatGPT and GPT4, have shown strong abilities in multilingual translations, without being explicitly trained on parallel corpora. It is interesting how the LLMs obtain their ability to carry out translation instructions for different languages. In this paper, we present a detailed analysis by finetuning a multilingual pretrained language model, XGLM-7B, to perform multilingual translation following given instructions. Firstly, we show that multilingual LLMs have stronger translation abilities than previously demonstrated. For a certain language, the performance depends on its similarity to English and the amount of data used in the pretraining phase. Secondly, we find that LLMs' ability to carry out translation instructions relies on the understanding of translation instructions and the alignment among different languages. With multilingual finetuning, LLMs could learn to perform the translation task well even for those language pairs unseen during the instruction tuning phase.

Transformer-based language models, including ChatGPT, have demonstrated exceptional performance in various natural language generation tasks. However, there has been limited research evaluating ChatGPT's keyphrase generation ability, which involves identifying informative phrases that accurately reflect a document's content. This study seeks to address this gap by comparing ChatGPT's keyphrase generation performance with state-of-the-art models, while also testing its potential as a solution for two significant challenges in the field: domain adaptation and keyphrase generation from long documents. We conducted experiments on six publicly available datasets from scientific articles and news domains, analyzing performance on both short and long documents. Our results show that ChatGPT outperforms current state-of-the-art models in all tested datasets and environments, generating high-quality keyphrases that adapt well to diverse domains and document lengths.

Physicians considering clinical trials for their patients are met with the laborious process of checking many text based eligibility criteria. Large Language Models (LLMs) have shown to perform well for clinical information extraction and clinical reasoning, including medical tests, but not yet in real-world scenarios. This paper investigates the use of InstructGPT to assist physicians in determining eligibility for clinical trials based on a patient's summarised medical profile. Using a prompting strategy combining one-shot, selection-inference and chain-of-thought techniques, we investigate the performance of LLMs on 10 synthetically created patient profiles. Performance is evaluated at four levels: ability to identify screenable eligibility criteria from a trial given a medical profile; ability to classify for each individual criterion whether the patient qualifies; the overall classification whether a patient is eligible for a clinical trial and the percentage of criteria to be screened by physician. We evaluated against 146 clinical trials and a total of 4,135 eligibility criteria. The LLM was able to correctly identify the screenability of 72% (2,994/4,135) of the criteria. Additionally, 72% (341/471) of the screenable criteria were evaluated correctly. The resulting trial level classification as eligible or ineligible resulted in a recall of 0.5. By leveraging LLMs with a physician-in-the-loop, a recall of 1.0 and precision of 0.71 on clinical trial level can be achieved while reducing the amount of criteria to be checked by an estimated 90%. LLMs can be used to assist physicians with pre-screening of patients for clinical trials. By forcing instruction-tuned LLMs to produce chain-of-thought responses, the reasoning can be made transparent to and the decision process becomes amenable by physicians, thereby making such a system feasible for use in real-world scenarios.

Many deep learning applications benefit from using large models with billions of parameters. Training these models is notoriously expensive due to the need for specialized HPC clusters. In this work, we consider alternative setups for training large models: using cheap "preemptible" instances or pooling existing resources from multiple regions. We analyze the performance of existing model-parallel algorithms in these conditions and find configurations where training larger models becomes less communication-intensive. Based on these findings, we propose SWARM parallelism, a model-parallel training algorithm designed for poorly connected, heterogeneous and unreliable devices. SWARM creates temporary randomized pipelines between nodes that are rebalanced in case of failure. We empirically validate our findings and compare SWARM parallelism with existing large-scale training approaches. Finally, we combine our insights with compression strategies to train a large Transformer language model with 1B shared parameters (approximately 13B before sharing) on preemptible T4 GPUs with less than 200Mb/s network.

OpenAI, the developer of ChatGPT, has chosen London as the location for its first international office in a boost to the UK's attempts to stay competitive in the artificial intelligence race. The San Francisco-based company behind the popular chatbot said on Wednesday that it would start its expansion outside the US in the UK capital. OpenAI said the UK office would reinforce efforts to create "safe AGI". AGI refers to artificial general intelligence, or a highly intelligent AI system that OpenAI's chief executive, Sam Altman, has described as "generally smarter than humans". "We are thrilled to extend our research and development footprint into London, a city globally renowned for its rich culture and exceptional talent pool," said Diane Yoon, OpenAI's head of human resources.