Medicine, by its nature, is a multifaceted domain that requires the synthesis of information across various modalities. Medical generative vision-language models (VLMs) make a first step in this direction and promise many exciting clinical applications. However, existing models typically have to be fine-tuned on sizeable down-stream datasets, which poses a significant limitation as in many medical applications data is scarce, necessitating models that are capable of learning from few examples in real-time. Here we propose Med-Flamingo, a multimodal few-shot learner adapted to the medical domain. Based on OpenFlamingo-9B, we continue pre-training on paired and interleaved medical image-text data from publications and textbooks. Med-Flamingo unlocks few-shot generative medical visual question answering (VQA) abilities, which we evaluate on several datasets including a novel challenging open-ended VQA dataset of visual USMLE-style problems. Furthermore, we conduct the first human evaluation for generative medical VQA where physicians review the problems and blinded generations in an interactive app. Med-Flamingo improves performance in generative medical VQA by up to 20\% in clinician's rating and firstly enables multimodal medical few-shot adaptations, such as rationale generation. We release our model, code, and evaluation app under https://github.com/snap-stanford/med-flamingo.

Large language models (LLMs) have shown the potential to be integrated into human daily lives. Therefore, user preference is the most critical criterion for assessing LLMs' performance in real-world scenarios. However, existing benchmarks mainly focus on measuring models' accuracy using multi-choice questions, which limits the understanding of their capabilities in real applications. We fill this gap by proposing a comprehensive Chinese benchmark SuperCLUE, named after another popular Chinese LLM benchmark CLUE. SuperCLUE encompasses three sub-tasks: actual users' queries and ratings derived from an LLM battle platform (CArena), open-ended questions with single and multiple-turn dialogues (OPEN), and closed-ended questions with the same stems as open-ended single-turn ones (CLOSE). Our study shows that accuracy on closed-ended questions is insufficient to reflect human preferences achieved on open-ended ones. At the same time, they can complement each other to predict actual user preferences. We also demonstrate that GPT-4 is a reliable judge to automatically evaluate human preferences on open-ended questions in a Chinese context. Our benchmark will be released at https://www.CLUEbenchmarks.com

We present TransNormerLLM, the first linear attention-based Large Language Model (LLM) that outperforms conventional softmax attention-based models in terms of both accuracy and efficiency. TransNormerLLM evolves from the previous linear attention architecture TransNormer by making advanced modifications that include positional embedding, linear attention acceleration, gating mechanism, tensor normalization, inference acceleration and stabilization. Specifically, we use LRPE together with an exponential decay to avoid attention dilution issues while allowing the model to retain global interactions between tokens. Additionally, we propose Lightning Attention, a cutting-edge technique that accelerates linear attention by more than twice in runtime and reduces memory usage by a remarkable four times. To further enhance the performance of TransNormer, we leverage a gating mechanism to smooth training and a new tensor normalization scheme to accelerate the model, resulting in an impressive acceleration of over 20%. Furthermore, we have developed a robust inference algorithm that ensures numerical stability and consistent inference speed, regardless of the sequence length, showcasing superior efficiency during both training and inference stages. Scalability is at the heart of our model's design, enabling seamless deployment on large-scale clusters and facilitating expansion to even more extensive models, all while maintaining outstanding performance metrics. Rigorous validation of our model design is achieved through a series of comprehensive experiments on our self-collected corpus, boasting a size exceeding 6TB and containing over 2 trillion tokens. To ensure data quality and relevance, we implement a new self-cleaning strategy to filter our collected data. Our pre-trained models will be released to foster community advancements in efficient LLMs.

Large Language Models for Code (Code LLM) are flourishing. New and powerful models are released on a weekly basis, demonstrating remarkable performance on the code generation task. Various approaches have been proposed to boost the code generation performance of pre-trained Code LLMs, such as supervised fine-tuning, instruction tuning, reinforcement learning, etc. In this paper, we propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation. Under this framework, we present PanGu-Coder2, which achieves 62.20% pass@1 on the OpenAI HumanEval benchmark. Furthermore, through an extensive evaluation on CoderEval and LeetCode benchmarks, we show that PanGu-Coder2 consistently outperforms all previous Code LLMs.

In-context learning, which offers substantial advantages over fine-tuning, is predominantly observed in decoder-only models, while encoder-decoder (i.e., seq2seq) models excel in methods that rely on weight updates. Recently, a few studies have demonstrated the feasibility of few-shot learning with seq2seq models; however, this has been limited to tasks that align well with the seq2seq architecture, such as summarization and translation. Inspired by these initial studies, we provide a first-ever extensive experiment comparing the in-context few-shot learning capabilities of decoder-only and encoder-decoder models on a broad range of tasks. Furthermore, we propose two methods to more effectively elicit in-context learning ability in seq2seq models: objective-aligned prompting and a fusion-based approach. Remarkably, our approach outperforms a decoder-only model that is six times larger and exhibits significant performance improvements compared to conventional seq2seq models across a variety of settings. We posit that, with the right configuration and prompt design, seq2seq models can be highly effective few-shot learners for a wide spectrum of applications.

In the rapidly growing field of electronic design automation (EDA), professional software such as KiCad, Cadence , and Altium Designer provide increasingly extensive design functionalities. However, the intricate command structure and high learning curve create a barrier, particularly for novice printed circuit board (PCB) designers. This results in difficulties in selecting appropriate functions or plugins for varying design purposes, compounded by the lack of intuitive learning methods beyond traditional documentation, videos, and online forums. To address this challenge, an artificial intelligence (AI) interaction assist plugin for EDA software named SmartonAl is developed here, also KiCad is taken as the first example. SmartonAI is inspired by the HuggingGPT framework and employs large language models, such as GPT and BERT, to facilitate task planning and execution. On receiving a designer request, SmartonAI conducts a task breakdown and efficiently executes relevant subtasks, such as analysis of help documentation paragraphs and execution of different plugins, along with leveraging the built-in schematic and PCB manipulation functions in both SmartonAl itself and software. Our preliminary results demonstrate that SmartonAI can significantly streamline the PCB design process by simplifying complex commands into intuitive language-based interactions. By harnessing the powerful language capabilities of ChatGPT and the rich design functions of KiCad, the plugin effectively bridges the gap between complex EDA software and user-friendly interaction. Meanwhile, the new paradigm behind SmartonAI can also extend to other complex software systems, illustrating the immense potential of AI-assisted user interfaces in advancing digital interactions across various domains.

Large language models (LLMs) have been widely employed for graph-to-text generation tasks. However, the process of finetuning LLMs requires significant training resources and annotation work. In this paper, we explore the capability of generative models to generate descriptive text from graph data in a zero-shot setting. Specifically, we evaluate GPT-3 and ChatGPT on two graph-to-text datasets and compare their performance with that of finetuned LLM models such as T5 and BART. Our results demonstrate that generative models are capable of generating fluent and coherent text, achieving BLEU scores of 10.57 and 11.08 for the AGENDA and WebNLG datasets, respectively. However, our error analysis reveals that generative models still struggle with understanding the semantic relations between entities, and they also tend to generate text with hallucinations or irrelevant information. As a part of error analysis, we utilize BERT to detect machine-generated text and achieve high macro-F1 scores. We have made the text generated by generative models publicly available.

In-context learning (ICL) for large language models has proven to be a powerful approach for many natural language processing tasks. However, determining the best method to select examples for ICL is nontrivial as the results can vary greatly depending on the quality, quantity, and order of examples used. In this paper, we conduct a case study on text simplification (TS) to investigate how to select the best and most robust examples for ICL. We propose Metric-Based in-context Learning (MBL) method that utilizes commonly used TS metrics such as SARI, compression ratio, and BERT-Precision for selection. Through an extensive set of experiments with various-sized GPT models on standard TS benchmarks such as TurkCorpus and ASSET, we show that examples selected by the top SARI scores perform the best on larger models such as GPT-175B, while the compression ratio generally performs better on smaller models such as GPT-13B and GPT-6.7B. Furthermore, we demonstrate that MBL is generally robust to example orderings and out-of-domain test sets, and outperforms strong baselines and state-of-the-art finetuned language models. Finally, we show that the behaviour of large GPT models can be implicitly controlled by the chosen metric. Our research provides a new framework for selecting examples in ICL, and demonstrates its effectiveness in text simplification tasks, breaking new ground for more accurate and efficient NLG systems.

The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP). LLMs have revolutionized a multitude of domains, and they have made a significant impact in the medical field. Large language models are now more abundant than ever, and many of these models exhibit bilingual capabilities, proficient in both English and Chinese. However, a comprehensive evaluation of these models remains to be conducted. This lack of assessment is especially apparent within the context of radiology NLP. This study seeks to bridge this gap by critically evaluating thirty two LLMs in interpreting radiology reports, a crucial component of radiology NLP. Specifically, the ability to derive impressions from radiologic findings is assessed. The outcomes of this evaluation provide key insights into the performance, strengths, and weaknesses of these LLMs, informing their practical applications within the medical domain.

Large Language Models (LLMs) have demonstrated remarkable performance on various quantitative reasoning and knowledge benchmarks. However, many of these benchmarks are losing utility as LLMs get increasingly high scores, despite not yet reaching expert performance in these domains. We introduce ARB, a novel benchmark composed of advanced reasoning problems in multiple fields. ARB presents a more challenging test than prior benchmarks, featuring problems in mathematics, physics, biology, chemistry, and law. As a subset of ARB, we introduce a challenging set of math and physics problems which require advanced symbolic reasoning and domain knowledge. We evaluate recent models such as GPT-4 and Claude on ARB and demonstrate that current models score well below 50% on more demanding tasks. In order to improve both automatic and assisted evaluation capabilities, we introduce a rubric-based evaluation approach, allowing GPT-4 to score its own intermediate reasoning steps. Further, we conduct a human evaluation of the symbolic subset of ARB, finding promising agreement between annotators and GPT-4 rubric evaluation scores.