Since late 2022, Large Language Models (LLMs) have become very prominent with LLMs like ChatGPT and Bard receiving millions of users. Hundreds of new LLMs are announced each week, many of which are deposited to Hugging Face, a repository of machine learning models and datasets. To date, nearly 16,000 Text Generation models have been uploaded to the site. Given the huge influx of LLMs, it is of interest to know which LLM backbones, settings, training methods, and families are popular or trending. However, there is no comprehensive index of LLMs available. We take advantage of the relatively systematic nomenclature of Hugging Face LLMs to perform hierarchical clustering and identify communities amongst LLMs using n-grams and term frequency-inverse document frequency. Our methods successfully identify families of LLMs and accurately cluster LLMs into meaningful subgroups. We present a public web application to navigate and explore Constellation, our atlas of 15,821 LLMs. Constellation rapidly generates a variety of visualizations, namely dendrograms, graphs, word clouds, and scatter plots. Constellation is available at the following link: https://constellation.sites.stanford.edu/.

The integration of natural language processing (NLP) technologies into educational applications has shown promising results, particularly in the language learning domain. Recently, many spoken open-domain chatbots have been used as speaking partners, helping language learners improve their language skills. However, one of the significant challenges is the high word-error-rate (WER) when recognizing non-native/non-fluent speech, which interrupts conversation flow and leads to disappointment for learners. This paper explores the use of GPT4 for ASR error correction in conversational settings. In addition to WER, we propose to use semantic textual similarity (STS) and next response sensibility (NRS) metrics to evaluate the impact of error correction models on the quality of the conversation. We find that transcriptions corrected by GPT4 lead to higher conversation quality, despite an increase in WER. GPT4 also outperforms standard error correction methods without the need for in-domain training data.

Research in Image Generation has recently made significant progress, particularly boosted by the introduction of Vision-Language models which are able to produce high-quality visual content based on textual inputs. Despite ongoing advancements in terms of generation quality and realism, no methodical frameworks have been defined yet to quantitatively measure the quality of the generated content and the adherence with the prompted requests: so far, only human-based evaluations have been adopted for quality satisfaction and for comparing different generative methods. We introduce a novel automated method for Visual Concept Evaluation (ViCE), i.e. to assess consistency between a generated/edited image and the corresponding prompt/instructions, with a process inspired by the human cognitive behaviour. ViCE combines the strengths of Large Language Models (LLMs) and Visual Question Answering (VQA) into a unified pipeline, aiming to replicate the human cognitive process in quality assessment. This method outlines visual concepts, formulates image-specific verification questions, utilizes the Q&A system to investigate the image, and scores the combined outcome. Although this brave new hypothesis of mimicking humans in the image evaluation process is in its preliminary assessment stage, results are promising and open the door to a new form of automatic evaluation which could have significant impact as the image generation or the image target editing tasks become more and more sophisticated.

In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. Our models outperform open-source chat models on most benchmarks we tested, and based on our human evaluations for helpfulness and safety, may be a suitable substitute for closed-source models. We provide a detailed description of our approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on our work and contribute to the responsible development of LLMs.

Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity, rendering the maximum sequence length restricted. To address this issue, we introduce LongNet, a Transformer variant that can scale sequence length to more than 1 billion tokens, without sacrificing the performance on shorter sequences. Specifically, we propose dilated attention, which expands the attentive field exponentially as the distance grows. LongNet has significant advantages: 1) it has a linear computation complexity and a logarithm dependency between any two tokens in a sequence; 2) it can be served as a distributed trainer for extremely long sequences; 3) its dilated attention is a drop-in replacement for standard attention, which can be seamlessly integrated with the existing Transformer-based optimization. Experiments results demonstrate that LongNet yields strong performance on both long-sequence modeling and general language tasks. Our work opens up new possibilities for modeling very long sequences, e.g., treating a whole corpus or even the entire Internet as a sequence.

This paper presents a performance comparison of three large language models (LLMs), namely OpenAI ChatGPT, Microsoft Bing Chat (BingChat), and Google Bard, on the VNHSGE English dataset. The performance of BingChat, Bard, and ChatGPT (GPT-3.5) is 92.4\%, 86\%, and 79.2\%, respectively. The results show that BingChat is better than ChatGPT and Bard. Therefore, BingChat and Bard can replace ChatGPT while ChatGPT is not yet officially available in Vietnam. The results also indicate that BingChat, Bard and ChatGPT outperform Vietnamese students in English language proficiency. The findings of this study contribute to the understanding of the potential of LLMs in English language education. The remarkable performance of ChatGPT, BingChat, and Bard demonstrates their potential as effective tools for teaching and learning English at the high school level.

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.

The rapid advancement in natural language processing (NLP) has led to the development of large language models (LLMs), such as BERT [2], GPT-3 [3], and Codex [4], that are revolutionizing a wide range of applications. These models have achieved remarkable results in various tasks such as text generation, machine translation, and code synthesis, among others. A recent addition to this collection of models was the OpenAI ChatGPT [1], a pretrained generative text model which was finetuned using human feedback. Unlike previous models which operate mostly upon a single prompt, ChatGPT provides particularly impressive interaction skills through dialog, combining text generation with code synthesis. Our goal in this paper is to investigate if and how the abilities of ChatGPT can generalize to the domain of robotics. Robotics systems, unlike text-only applications, require a deep understanding of real-world physics, environmental context, and the ability to perform physical actions. A generative robotics model needs to have a robust commonsense knowledge and a sophisticated world model, and the ability to interact with users to interpret and execute commands in ways that are physically possible and that makes sense in the real world. These challenges fall beyond the original scope of language models, as they must not only understand the meaning of a given text, but also translate the intent into a logical sequence of physical actions. In recent years there have been different attempts to incorporate language into robotics systems.

Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

Recently, various illustrative examples have shown the impressive ability of generative large language models (LLMs) to perform NLP related tasks. ChatGPT undoubtedly is the most representative model. We empirically evaluate ChatGPT's performance on requirements information retrieval (IR) tasks to derive insights into designing or developing more effective requirements retrieval methods or tools based on generative LLMs. We design an evaluation framework considering four different combinations of two popular IR tasks and two common artifact types. Under zero-shot setting, evaluation results reveal ChatGPT's promising ability to retrieve requirements relevant information (high recall) and limited ability to retrieve more specific requirements information (low precision). Our evaluation of ChatGPT on requirements IR under zero-shot setting provides preliminary evidence for designing or developing more effective requirements IR methods or tools based on LLMs.