In this study, we present a novel dataset for training machine learning models translating between OpenMP Fortran and C++ code. To ensure reliability and applicability, the dataset is created from a range of representative open-source OpenMP benchmarks. It is also refined using a meticulous code similarity test. The effectiveness of our dataset is assessed using both quantitative (CodeBLEU) and qualitative (human evaluation) methods. We showcase how this dataset significantly elevates the translation competencies of large language models (LLMs). Specifically, models without prior coding knowledge experienced a boost of $\mathbf{\times~5.1}$ in their CodeBLEU scores, while models with some coding familiarity saw an impressive $\mathbf{\times~9.9}$-fold increase. The best fine-tuned model using our dataset outperforms GPT-4. It is also reaching human-level accuracy. This work underscores the immense potential of our dataset in propelling advancements in the domain of code translation for high-performance computing. The dataset is accessible at \href{https://github.com/bin123apple/Fortran-CPP-HPC-code-translation-dataset}{OpenMP-Fortran-CPP-Translation}.

Large Language Models (LLMs) exploit fine-tuning as a technique to adapt to diverse goals, thanks to task-specific training data. Task specificity should go hand in hand with domain orientation, that is, the specialization of an LLM to accurately address the tasks of a given realm of interest. However, models are usually fine-tuned over publicly available data or, at most, over ground data from databases, ignoring business-level definitions and domain experience. On the other hand, Enterprise Knowledge Graphs (EKGs) are able to capture and augment such domain knowledge via ontological reasoning. With the goal of combining LLM flexibility with the domain orientation of EKGs, we propose a novel neurosymbolic architecture that leverages the power of ontological reasoning to build task- and domain-specific corpora for LLM fine-tuning.

ChatGPT has demonstrated remarkable capabilities across various natural language processing (NLP) tasks. However, its potential for inferring dynamic network structures from temporal textual data, specifically financial news, remains an unexplored frontier. In this research, we introduce a novel framework that leverages ChatGPT's graph inference capabilities to enhance Graph Neural Networks (GNN). Our framework adeptly extracts evolving network structures from textual data, and incorporates these networks into graph neural networks for subsequent predictive tasks. The experimental results from stock movement forecasting indicate our model has consistently outperformed the state-of-the-art Deep Learning-based benchmarks. Furthermore, the portfolios constructed based on our model's outputs demonstrate higher annualized cumulative returns, alongside reduced volatility and maximum drawdown. This superior performance highlights the potential of ChatGPT for text-based network inferences and underscores its promising implications for the financial sector.

User behavior analysis is crucial in human-centered AI applications. In this field, the collection of sufficient and high-quality user behavior data has always been a fundamental yet challenging problem. An intuitive idea to address this problem is automatically simulating the user behaviors. However, due to the subjective and complex nature of human cognitive processes, reliably simulating the user behavior is difficult. Recently, large language models (LLM) have obtained remarkable successes, showing great potential to achieve human-like intelligence. We argue that these models present significant opportunities for reliable user simulation, and have the potential to revolutionize traditional study paradigms in user behavior analysis. In this paper, we take recommender system as an example to explore the potential of using LLM for user simulation. Specifically, we regard each user as an LLM-based autonomous agent, and let different agents freely communicate, behave and evolve in a virtual simulator called RecAgent. For comprehensively simulation, we not only consider the behaviors within the recommender system (\emph{e.g.}, item browsing and clicking), but also accounts for external influential factors, such as, friend chatting and social advertisement. Our simulator contains at most 1000 agents, and each agent is composed of a profiling module, a memory module and an action module, enabling it to behave consistently, reasonably and reliably. In addition, to more flexibly operate our simulator, we also design two global functions including real-human playing and system intervention. To evaluate the effectiveness of our simulator, we conduct extensive experiments from both agent and system perspectives. In order to advance this direction, we have released our project at {https://github.com/RUC-GSAI/YuLan-Rec}.

Pre-trained language models(PLM) have made impressive results in various NLP tasks. It has been revealed that one of the key factors to their success is the parameters of these models implicitly learn all kinds of knowledge during pre-training. However, encoding knowledge implicitly in the model parameters has two fundamental drawbacks. First, the knowledge is neither editable nor scalable once the model is trained, which is especially problematic in that knowledge is consistently evolving. Second, it lacks interpretability and prevents humans from understanding which knowledge PLM requires for a certain problem. In this paper, we introduce PlugLM, a pre-training model with differentiable plug-in memory(DPM). The key intuition is to decouple the knowledge storage from model parameters with an editable and scalable key-value memory and leverage knowledge in an explainable manner by knowledge retrieval in the DPM. To justify this design choice, we conduct evaluations in three settings including: (1) domain adaptation. PlugLM obtains 3.95 F1 improvements across four domains on average without any in-domain pre-training. (2) knowledge update. PlugLM could absorb new knowledge in a training-free way after pre-training is done. (3) in-task knowledge learning. PlugLM could be further improved by incorporating training samples into DPM with knowledge prompting.

Interactions between humans are diverse and context-dependent, but previous works have treated them as categorical, disregarding the heavy tail of possible interactions. We propose a new paradigm of learning human-human interactions as free text from a single still image, allowing for flexibility in modeling the unlimited space of situations and relationships between people. To overcome the absence of data labelled specifically for this task, we use knowledge distillation applied to synthetic caption data produced by a large language model without explicit supervision. We show that the pseudo-labels produced by this procedure can be used to train a captioning model to effectively understand human-human interactions in images, as measured by a variety of metrics that measure textual and semantic faithfulness and factual groundedness of our predictions. We further show that our approach outperforms SOTA image captioning and situation recognition models on this task. We will release our code and pseudo-labels along with Waldo and Wenda, a manually-curated test set for still image human-human interaction understanding.

Evaluating the general abilities of foundation models to tackle human-level tasks is a vital aspect of their development and application in the pursuit of Artificial General Intelligence (AGI). Traditional benchmarks, which rely on artificial datasets, may not accurately represent human-level capabilities. In this paper, we introduce AGIEval, a novel benchmark specifically designed to assess foundation model in the context of human-centric standardized exams, such as college entrance exams, law school admission tests, math competitions, and lawyer qualification tests. We evaluate several state-of-the-art foundation models, including GPT-4, ChatGPT, and Text-Davinci-003, using this benchmark. Impressively, GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92.5% accuracy on the English test of the Chinese national college entrance exam. This demonstrates the extraordinary performance of contemporary foundation models. In contrast, we also find that GPT-4 is less proficient in tasks that require complex reasoning or specific domain knowledge. Our comprehensive analyses of model capabilities (understanding, knowledge, reasoning, and calculation) reveal these models' strengths and limitations, providing valuable insights into future directions for enhancing their general capabilities. By concentrating on tasks pertinent to human cognition and decision-making, our benchmark delivers a more meaningful and robust evaluation of foundation models' performance in real-world scenarios. The data, code, and all model outputs are released in https://github.com/ruixiangcui/AGIEval.

Reasoning, as an essential ability for complex problem-solving, can provide back-end support for various real-world applications, such as medical diagnosis, negotiation, etc. This paper provides a comprehensive survey of cutting-edge research on reasoning with language model prompting. We introduce research works with comparisons and summaries and provide systematic resources to help beginners. We also discuss the potential reasons for emerging such reasoning abilities and highlight future research directions. Resources are available at https://github.com/zjunlp/Prompt4ReasoningPapers (updated periodically).

Software engineers have joined the ranks of copy editors, translators, and others who fear that they're about to be replaced by generative AI. But it might be surprising to learn that coders have been under threat before. New technologies have long promised to "disrupt" engineering, and these innovations have always failed to get rid of the need for human software developers. If anything, they often made these workers that much more indispensable. To understand where handwringing about the end of programmers comes from--and why it's overblown--we need to look back at the evolution of coding and computing.

Large language models (LLMs) are becoming increasingly relevant as a potential tool for healthcare, aiding communication between clinicians, researchers, and patients. However, traditional evaluations of LLMs on medical exam questions do not reflect the complexity of real patient-doctor interactions. An example of this complexity is the introduction of patient self-diagnosis, where a patient attempts to diagnose their own medical conditions from various sources. While the patient sometimes arrives at an accurate conclusion, they more often are led toward misdiagnosis due to the patient's over-emphasis on bias validating information. In this work we present a variety of LLMs with multiple-choice questions from United States medical board exams which are modified to include self-diagnostic reports from patients. Our findings highlight that when a patient proposes incorrect bias-validating information, the diagnostic accuracy of LLMs drop dramatically, revealing a high susceptibility to errors in self-diagnosis.