Parallel programs in high performance computing (HPC) continue to grow in complexity and scale in the exascale era. The diversity in hardware and parallel programming models make developing, optimizing, and maintaining parallel software even more burdensome for developers. One way to alleviate some of these burdens is with automated development and analysis tools. Such tools can perform complex and/or remedial tasks for developers that increase their productivity and decrease the chance for error. Until recently, such tools for code development and performance analysis have been limited in the complexity of tasks they can perform, especially for parallel programs. However, with recent advancements in language modeling, and the availability of large amounts of open-source code related data, these tools have started to utilize predictive language models to automate more complex tasks. In this paper, we show how large language models (LLMs) can be applied to tasks specific to high performance and scientific codes. We introduce a new dataset of HPC and scientific codes and use it to fine-tune several pre-trained models. We compare several pre-trained LLMs on HPC-related tasks and introduce a new model, HPC-Coder, fine-tuned on parallel codes. In our experiments, we show that this model can auto-complete HPC functions where generic models cannot, decorate for loops with OpenMP pragmas, and model performance changes in scientific application repositories as well as programming competition solutions.
Recommendation systems help users find matched items based on their previous behaviors. Personalized recommendation becomes challenging in the absence of historical user-item interactions, a practical problem for startups known as the system cold-start recommendation. While existing research addresses cold-start issues for either users or items, we still lack solutions for system cold-start scenarios. To tackle the problem, we propose PromptRec, a simple but effective approach based on in-context learning of language models, where we transform the recommendation task into the sentiment analysis task on natural language containing user and item profiles. However, this naive approach heavily relies on the strong in-context learning ability emerged from large language models, which could suffer from significant latency for online recommendations. To solve the challenge, we propose to enhance small language models for recommender systems with a data-centric pipeline, which consists of: (1) constructing a refined corpus for model pre-training; (2) constructing a decomposed prompt template via prompt pre-training. They correspond to the development of training data and inference data, respectively. The pipeline is supported by a theoretical framework that formalizes the connection between in-context recommendation and language modeling. To evaluate our approach, we introduce a cold-start recommendation benchmark, and the results demonstrate that the enhanced small language models can achieve comparable cold-start recommendation performance to that of large models with only $17\%$ of the inference time. To the best of our knowledge, this is the first study to tackle the system cold-start recommendation problem. We believe our findings will provide valuable insights for future works. The benchmark and implementations are available at https://github.com/JacksonWuxs/PromptRec.
Solving symbolic reasoning problems that require compositionality and systematicity is considered one of the key ingredients of human intelligence. However, symbolic reasoning is still a great challenge for deep learning models, which often cannot generalize the reasoning pattern to out-of-distribution test cases. In this work, we propose a hybrid system capable of solving arithmetic problems that require compositional and systematic reasoning over sequences of symbols. The model acquires such a skill by learning appropriate substitution rules, which are applied iteratively to the input string until the expression is completely resolved. We show that the proposed system can accurately solve nested arithmetical expressions even when trained only on a subset including the simplest cases, significantly outperforming both a sequence-to-sequence model trained end-to-end and a state-of-the-art large language model.
The biomedical field relies heavily on concept linking in various areas such as literature mining, graph alignment, information retrieval, question-answering, data, and knowledge integration. Although large language models (LLMs) have made significant strides in many natural language processing tasks, their effectiveness in biomedical concept mapping is yet to be fully explored. This research investigates a method that exploits the in-context learning (ICL) capabilities of large models for biomedical concept linking. The proposed approach adopts a two-stage retrieve-and-rank framework. Initially, biomedical concepts are embedded using language models, and then embedding similarity is utilized to retrieve the top candidates. These candidates' contextual information is subsequently incorporated into the prompt and processed by a large language model to re-rank the concepts. This approach achieved an accuracy of 90.% in BC5CDR disease entity normalization and 94.7% in chemical entity normalization, exhibiting a competitive performance relative to supervised learning methods. Further, it showed a significant improvement, with an over 20-point absolute increase in F1 score on an oncology matching dataset. Extensive qualitative assessments were conducted, and the benefits and potential shortcomings of using large language models within the biomedical domain were discussed. were discussed.
The advent of ChatGPT, a large language model-powered chatbot, has prompted questions about its potential implications for traditional search engines. In this study, we investigate the differences in user behavior when employing search engines and chatbot tools for information-seeking tasks. We carry out a randomized online experiment, dividing participants into two groups: one using a ChatGPT-like tool and the other using a Google Search-like tool. Our findings reveal that the ChatGPT group consistently spends less time on all tasks, with no significant difference in overall task performance between the groups. Notably, ChatGPT levels user search performance across different education levels and excels in answering straightforward questions and providing general solutions but falls short in fact-checking tasks. Users perceive ChatGPT's responses as having higher information quality compared to Google Search, despite displaying a similar level of trust in both tools. Furthermore, participants using ChatGPT report significantly better user experiences in terms of usefulness, enjoyment, and satisfaction, while perceived ease of use remains comparable between the two tools. However, ChatGPT may also lead to overreliance and generate or replicate misinformation, yielding inconsistent results. Our study offers valuable insights for search engine management and highlights opportunities for integrating chatbot technologies into search engine designs.
Information retrieval (IR) is essential in biomedical knowledge acquisition and clinical decision support. While recent progress has shown that language model encoders perform better semantic retrieval, training such models requires abundant query-article annotations that are difficult to obtain in biomedicine. As a result, most biomedical IR systems only conduct lexical matching. In response, we introduce MedCPT, a first-of-its-kind Contrastively Pre-trained Transformer model for zero-shot semantic IR in biomedicine. To train MedCPT, we collected an unprecedented scale of 255 million user click logs from PubMed. With such data, we use contrastive learning to train a pair of closely-integrated retriever and re-ranker. Experimental results show that MedCPT sets new state-of-the-art performance on six biomedical IR tasks, outperforming various baselines including much larger models such as GPT-3-sized cpt-text-XL. In addition, MedCPT also generates better biomedical article and sentence representations for semantic evaluations. As such, MedCPT can be readily applied to various real-world biomedical IR tasks.
Large language models(LLMS)have shown excellent text generation capabilities, capable of generating fluent human-like responses for many downstream tasks. However, applying large language models to real-world critical tasks remains challenging due to their susceptibility to hallucinations and inability to directly use external knowledge. To cope with the above challenges, this paper proposes PatternGPT, a pattern-driven text generation framework for Large Language Models. Firstly, the framework utilizes the extraction capability of Large Language Models to generate rich and diversified structured and formalized patterns, which facilitates the introduction of external knowledge to do the computation, and then draws on the idea of federated learning to use multiple agents to achieve the sharing in order to obtain more diversified patterns, and finally uses judgment criteria and optimization algorithm to search for high-quality patterns to guide the generation of models. Finally, external knowledge such as judgment criteria and optimization algorithms are used to search for high-quality patterns, and the searched patterns are used to guide model generation. This framework has the advantages of generating diversified patterns, protecting data privacy, combining external knowledge, and improving the quality of generation, which provides an effective method to optimize the text generation capability of large language models, and make it better applied to the field of intelligent dialogue and content generation.
This work builds together two popular blocks of neural architecture, namely convolutional layers and Transformers, for large language models (LLMs). Non-causal conformers are used ubiquitously in automatic speech recognition. This work aims to adapt these architectures in a causal setup for training LLMs. Transformers decoders effectively capture long-range dependencies over several modalities and form a core backbone of modern advancements in machine learning. Convolutional architectures have been popular in extracting features in domains such as raw 1-D signals, speech, and images, to name a few. In this paper, by combining local and global dependencies over latent representations using causal convolutional filters and Transformer, we achieve significant gains in performance. This work showcases a robust speech architecture that can be integrated and adapted in a causal setup beyond speech applications for large-scale language modeling.
The current era of natural language processing (NLP) has been defined by the prominence of pre-trained language models since the advent of BERT. A feature of BERT and models with similar architecture is the objective of masked language modeling, in which part of the input is intentionally masked and the model is trained to predict this piece of masked information. Data augmentation is a data-driven technique widely used in machine learning, including research areas like computer vision and natural language processing, to improve model performance by artificially augmenting the training data set by designated techniques. Masked language models (MLM), an essential training feature of BERT, have introduced a novel approach to perform effective pre-training on Transformer based models in natural language processing tasks. Recent studies have utilized masked language model to generate artificially augmented data for NLP downstream tasks. The experimental results show that Mask based data augmentation method provides a simple but efficient approach to improve the model performance. In this paper, we explore and discuss the broader utilization of these data augmentation methods based on MLM.
As malicious actors employ increasingly advanced and widespread bots to disseminate misinformation and manipulate public opinion, the detection of Twitter bots has become a crucial task. Though graph-based Twitter bot detection methods achieve state-of-the-art performance, we find that their inference depends on the neighbor users multi-hop away from the targets, and fetching neighbors is time-consuming and may introduce bias. At the same time, we find that after finetuning on Twitter bot detection, pretrained language models achieve competitive performance and do not require a graph structure during deployment. Inspired by this finding, we propose a novel bot detection framework LMBot that distills the knowledge of graph neural networks (GNNs) into language models (LMs) for graph-less deployment in Twitter bot detection to combat the challenge of data dependency. Moreover, LMBot is compatible with graph-based and graph-less datasets. Specifically, we first represent each user as a textual sequence and feed them into the LM for domain adaptation. For graph-based datasets, the output of LMs provides input features for the GNN, enabling it to optimize for bot detection and distill knowledge back to the LM in an iterative, mutually enhancing process. Armed with the LM, we can perform graph-less inference, which resolves the graph data dependency and sampling bias issues. For datasets without graph structure, we simply replace the GNN with an MLP, which has also shown strong performance. Our experiments demonstrate that LMBot achieves state-of-the-art performance on four Twitter bot detection benchmarks. Extensive studies also show that LMBot is more robust, versatile, and efficient compared to graph-based Twitter bot detection methods.
Classifier-Free Guidance (CFG) has recently emerged in text-to-image generation as a lightweight technique to encourage prompt-adherence in generations. In this work, we demonstrate that CFG can be used broadly as an inference-time technique in pure language modeling. We show that CFG (1) improves the performance of Pythia, GPT-2 and LLaMA-family models across an array of tasks: Q\&A, reasoning, code generation, and machine translation, achieving SOTA on LAMBADA with LLaMA-7B over PaLM-540B; (2) brings improvements equivalent to a model with twice the parameter-count; (3) can stack alongside other inference-time methods like Chain-of-Thought and Self-Consistency, yielding further improvements in difficult tasks; (4) can be used to increase the faithfulness and coherence of assistants in challenging form-driven and content-driven prompts: in a human evaluation we show a 75\% preference for GPT4All using CFG over baseline.
Computing homotopy groups of spheres has long been a fundamental objective in algebraic topology. Various theoretical and algorithmic approaches have been developed to tackle this problem. In this paper we take a step towards the goal of comprehending the group-theoretic structure of the generators of these homotopy groups by leveraging the power of machine learning. Specifically, in the simplicial group setting of Wu's formula, we reformulate the problem of generating simplicial cycles as a problem of sampling from the intersection of algorithmic datasets related to Dyck languages. We present and evaluate language modelling approaches that employ multi-label information for input sequences, along with the necessary group-theoretic toolkit and non-neural baselines.
Large Language Models (LLMs) have shown impressive abilities in many applications. When a concrete and precise answer is desired, it is important to have a quantitative estimation of the potential error rate. However, this can be challenging due to the text-in-text-out nature of generative models. We present a method based on Pareto optimization that generates a risk score to estimate the probability of error in an LLM response by integrating multiple sources of information. We prove theoretically that the error estimator optimized in our framework aligns with the LLM and the information sources in an Pareto optimal manner. Experimental results show that the risk scores estimated by our method are well correlated with the true LLM error rate, thus facilitating error correction. By dynamically combining with prompting strategies such as self-verification and information retrieval, we demonstrate the proposed method can be utilized to increase the performance of an LLM, surpassing state-of-the-art task specific models.
Terminology sources, such as controlled vocabularies, thesauri and classification systems, play a key role in digitizing cultural heritage. However, Information Retrieval (IR) systems that allow to query and explore these lexical resources often lack an adequate representation of the semantics behind the user's search, which can be conveyed through multiple expression modalities (e.g., images, keywords or textual descriptions). This paper presents the implementation of a new search engine for one of the most widely used iconography classification system, Iconclass. The novelty of this system is the use of a pre-trained vision-language model, namely CLIP, to retrieve and explore Iconclass concepts using visual or textual queries.
We introduce LyricWhiz, a robust, multilingual, and zero-shot automatic lyrics transcription method achieving state-of-the-art performance on various lyrics transcription datasets, even in challenging genres such as rock and metal. Our novel, training-free approach utilizes Whisper, a weakly supervised robust speech recognition model, and GPT-4, today's most performant chat-based large language model. In the proposed method, Whisper functions as the "ear" by transcribing the audio, while GPT-4 serves as the "brain," acting as an annotator with a strong performance for contextualized output selection and correction. Our experiments show that LyricWhiz significantly reduces Word Error Rate compared to existing methods in English and can effectively transcribe lyrics across multiple languages. Furthermore, we use LyricWhiz to create the first publicly available, large-scale, multilingual lyrics transcription dataset with a CC-BY-NC-SA copyright license, based on MTG-Jamendo, and offer a human-annotated subset for noise level estimation and evaluation. We anticipate that our proposed method and dataset will advance the development of multilingual lyrics transcription, a challenging and emerging task.
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.
We present Palm, a solution to the Long-Term Action Anticipation (LTA) task utilizing vision-language and large language models. Given an input video with annotated action periods, the LTA task aims to predict possible future actions. We hypothesize that an optimal solution should capture the interdependency between past and future actions, and be able to infer future actions based on the structure and dependency encoded in the past actions. Large language models have demonstrated remarkable commonsense-based reasoning ability. Inspired by that, Palm chains an image captioning model and a large language model. It predicts future actions based on frame descriptions and action labels extracted from the input videos. Our method outperforms other participants in the EGO4D LTA challenge and achieves the best performance in terms of action prediction. Our code is available at https://github.com/DanDoge/Palm
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 ~42% of them verbatim, in an expert-verified dataset of past performance changes made by C# developers.
We present the Chinese Elementary School Math Word Problems (CMATH) dataset, comprising 1.7k elementary school-level math word problems with detailed annotations, source from actual Chinese workbooks and exams. This dataset aims to provide a benchmark tool for assessing the following question: to what grade level of elementary school math do the abilities of popular large language models (LLMs) correspond? We evaluate a variety of popular LLMs, including both commercial and open-source options, and discover that only GPT-4 achieves success (accuracy $\geq$ 60\%) across all six elementary school grades, while other models falter at different grade levels. Furthermore, we assess the robustness of several top-performing LLMs by augmenting the original problems in the CMATH dataset with distracting information. Our findings reveal that GPT-4 is able to maintains robustness, while other model fail. We anticipate that our study will expose limitations in LLMs' arithmetic and reasoning capabilities, and promote their ongoing development and advancement.
Superconductivity allows electrical current to flow without any energy loss, and thus making solids superconducting is a grand goal of physics, material science, and electrical engineering. More than 16 Nobel Laureates have been awarded for their contribution to superconductivity research. Superconductors are valuable for sustainable development goals (SDGs), such as climate change mitigation, affordable and clean energy, industry, innovation and infrastructure, and so on. However, a unified physics theory explaining all superconductivity mechanism is still unknown. It is believed that superconductivity is microscopically due to not only molecular compositions but also the geometric crystal structure. Hence a new dataset, S2S, containing both crystal structures and superconducting critical temperature, is built upon SuperCon and Material Project. Based on this new dataset, we propose a novel model, S2SNet, which utilizes the attention mechanism for superconductivity prediction. To overcome the shortage of data, S2SNet is pre-trained on the whole Material Project dataset with Masked-Language Modeling (MLM). S2SNet makes a new state-of-the-art, with out-of-sample accuracy of 92% and Area Under Curve (AUC) of 0.92. To the best of our knowledge, S2SNet is the first work to predict superconductivity with only information of crystal structures. This work is beneficial to superconductivity discovery and further SDGs. Code and datasets are available in https://github.com/zjuKeLiu/S2SNet