To extend the context length of Transformer-based large language models (LLMs) and improve comprehension capabilities, we often face limitations due to computational resources and bounded memory storage capacity. This work introduces a method called Recurrent Context Compression (RCC), designed to efficiently expand the context window length of LLMs within constrained storage space. We also investigate the issue of poor model responses when both instructions and context are compressed in downstream tasks, and propose an instruction reconstruction method to mitigate this problem. We validated the effectiveness of our approach on multiple tasks, achieving a compression rate of up to 32x on text reconstruction tasks with a BLEU4 score close to 0.95, and nearly 100\% accuracy on a passkey retrieval task with a sequence length of 1M. Finally, our method demonstrated competitive performance in long-text question-answering tasks compared to non-compressed methods, while significantly saving storage resources in long-text inference tasks. Our code, models, and demo are available at https://github.com/WUHU-G/RCC_Transformer

The capability of large language models (LLMs) to generate, debug, and explain code has sparked the interest of researchers and educators in undergraduate programming, with many anticipating their transformative potential in programming education. However, decisions about why and how to use LLMs in programming education may involve more than just the assessment of an LLM's technical capabilities. Using the social shaping of technology theory as a guiding framework, our study explores how students' social perceptions influence their own LLM usage. We then examine the correlation of self-reported LLM usage with students' self-efficacy and midterm performances in an undergraduate programming course. Triangulating data from an anonymous end-of-course student survey (n = 158), a mid-course self-efficacy survey (n=158), student interviews (n = 10), self-reported LLM usage on homework, and midterm performances, we discovered that students' use of LLMs was associated with their expectations for their future careers and their perceptions of peer usage. Additionally, early self-reported LLM usage in our context correlated with lower self-efficacy and lower midterm scores, while students' perceived over-reliance on LLMs, rather than their usage itself, correlated with decreased self-efficacy later in the course.

Food is foundational to human life, serving not only as a source of nourishment but also as a cornerstone of cultural identity and social interaction. As the complexity of global dietary needs and preferences grows, food intelligence is needed to enable food perception and reasoning for various tasks, ranging from recipe generation and dietary recommendation to diet-disease correlation discovery and understanding. Towards this goal, for powerful capabilities across various domains and tasks in Large Language Models (LLMs), we introduce Food-oriented LLM FoodSky to comprehend food data through perception and reasoning. Considering the complexity and typicality of Chinese cuisine, we first construct one comprehensive Chinese food corpus FoodEarth from various authoritative sources, which can be leveraged by FoodSky to achieve deep understanding of food-related data. We then propose Topic-based Selective State Space Model (TS3M) and the Hierarchical Topic Retrieval Augmented Generation (HTRAG) mechanism to enhance FoodSky in capturing fine-grained food semantics and generating context-aware food-relevant text, respectively. Our extensive evaluations demonstrate that FoodSky significantly outperforms general-purpose LLMs in both chef and dietetic examinations, with an accuracy of 67.2% and 66.4% on the Chinese National Chef Exam and the National Dietetic Exam, respectively. FoodSky not only promises to enhance culinary creativity and promote healthier eating patterns, but also sets a new standard for domain-specific LLMs that address complex real-world issues in the food domain. An online demonstration of FoodSky is available at http://222.92.101.211:8200.

Developing therapeutics is a lengthy and expensive process that requires the satisfaction of many different criteria, and AI models capable of expediting the process would be invaluable. However, the majority of current AI approaches address only a narrowly defined set of tasks, often circumscribed within a particular domain. To bridge this gap, we introduce Tx-LLM, a generalist large language model (LLM) fine-tuned from PaLM-2 which encodes knowledge about diverse therapeutic modalities. Tx-LLM is trained using a collection of 709 datasets that target 66 tasks spanning various stages of the drug discovery pipeline. Using a single set of weights, Tx-LLM simultaneously processes a wide variety of chemical or biological entities(small molecules, proteins, nucleic acids, cell lines, diseases) interleaved with free-text, allowing it to predict a broad range of associated properties, achieving competitive with state-of-the-art (SOTA) performance on 43 out of 66 tasks and exceeding SOTA on 22. Among these, Tx-LLM is particularly powerful and exceeds best-in-class performance on average for tasks combining molecular SMILES representations with text such as cell line names or disease names, likely due to context learned during pretraining. We observe evidence of positive transfer between tasks with diverse drug types (e.g.,tasks involving small molecules and tasks involving proteins), and we study the impact of model size, domain finetuning, and prompting strategies on performance. We believe Tx-LLM represents an important step towards LLMs encoding biochemical knowledge and could have a future role as an end-to-end tool across the drug discovery development pipeline.

Policy documents, such as legislation, regulations, and executive orders, are crucial in shaping society. However, their length and complexity make interpretation and application challenging and time-consuming. Artificial intelligence (AI), particularly large language models (LLMs), has the potential to automate the process of analyzing these documents, improving accuracy and efficiency. This study aims to evaluate the potential of AI in streamlining policy analysis and to identify the strengths and limitations of current AI approaches. The research focuses on question answering and tasks involving content extraction from policy documents. A case study was conducted using Executive Order 14110 on "Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence" as a test case. Four commercial AI systems were used to analyze the document and answer a set of representative policy questions. The performance of the AI systems was compared to manual analysis conducted by human experts. The study found that two AI systems, Gemini 1.5 Pro and Claude 3 Opus, demonstrated significant potential for supporting policy analysis, providing accurate and reliable information extraction from complex documents. They performed comparably to human analysts but with significantly higher efficiency. However, achieving reproducibility remains a challenge, necessitating further research and development.

The increasing size of large language models (LLMs) traditionally requires low-precision integer formats to meet strict latency and power demands. Yet recently, alternative formats such as Normal Float (NF4) have increased model accuracy at the cost of increased chip area. In this work, we first conduct a large-scale analysis of LLM weights and activations across 30 networks and conclude that most distributions follow a Student's t-distribution. We then derive a new theoretically optimal format, Student Float (SF4), that improves over NF4 across modern LLMs, for example increasing the average accuracy on LLaMA2-7B by 0.76% across tasks. Using this format as a high-accuracy reference, we then propose augmenting E2M1 with two variants of supernormal support for higher model accuracy. Finally, we explore the quality and efficiency frontier across 11 datatypes by evaluating their model accuracy and hardware complexity. We discover a Pareto curve composed of INT4, E2M1, and E2M1 with supernormal support, which offers a continuous tradeoff between model accuracy and chip area. For example, E2M1 with supernormal support increases the accuracy of Phi-2 by up to 2.19% with 1.22% area overhead, enabling more LLM-based applications to be run at four bits. The supporting code is hosted at https://github.com/cornell-zhang/llm-datatypes.

The latest paradigm shift in software development brings in the innovation and automation afforded by Large Language Models (LLMs), showcased by Generative Pre-trained Transformer (GPT), which has shown remarkable capacity to generate code autonomously, significantly reducing the manual effort required for various programming tasks. Although, the potential benefits of LLM-generated code are vast, most notably in efficiency and rapid prototyping, as LLMs become increasingly integrated into the software development lifecycle and hence the supply chain, complex and multifaceted challenges arise as the code generated from these language models carry profound questions on quality and correctness. Research is required to comprehensively explore these critical concerns surrounding LLM-generated code. In this paper, we propose a novel solution called metamorphic prompt testing to address these challenges. Our intuitive observation is that intrinsic consistency always exists among correct code pieces but may not exist among flawed code pieces, so we can detect flaws in the code by detecting inconsistencies. Therefore, we can vary a given prompt to multiple prompts with paraphrasing, and to ask the LLM to acquire multiple versions of generated code, so that we can validate whether the semantic relations still hold in the acquired code through cross-validation. Our evaluation on HumanEval shows that metamorphic prompt testing is able to detect 75 percent of the erroneous programs generated by GPT-4, with a false positive rate of 8.6 percent.

Many commercial and open-source models claim to detect machine-generated text with extremely high accuracy (99% or more). However, very few of these detectors are evaluated on shared benchmark datasets and even when they are, the datasets used for evaluation are insufficiently challenging-lacking variations in sampling strategy, adversarial attacks, and open-source generative models. In this work we present RAID: the largest and most challenging benchmark dataset for machine-generated text detection. RAID includes over 6 million generations spanning 11 models, 8 domains, 11 adversarial attacks and 4 decoding strategies. Using RAID, we evaluate the out-of-domain and adversarial robustness of 8 open- and 4 closed-source detectors and find that current detectors are easily fooled by adversarial attacks, variations in sampling strategies, repetition penalties, and unseen generative models. We release our data along with a leaderboard to encourage future research.

Training modern LLMs is extremely resource intensive, and customizing them for various deployment scenarios characterized by limited compute and memory resources through repeated training is impractical. In this paper, we introduce Flextron, a network architecture and post-training model optimization framework supporting flexible model deployment. The Flextron architecture utilizes a nested elastic structure to rapidly adapt to specific user-defined latency and accuracy targets during inference with no additional fine-tuning required. It is also input-adaptive, and can automatically route tokens through its sub-networks for improved performance and efficiency. We present a sample-efficient training method and associated routing algorithms for systematically transforming an existing trained LLM into a Flextron model. We evaluate Flextron on the GPT-3 and LLama-2 family of LLMs, and demonstrate superior performance over multiple end-to-end trained variants and other state-of-the-art elastic networks, all with a single pretraining run that consumes a mere 7.63% tokens compared to original pretraining.

Dense linear layers are the dominant computational bottleneck in foundation models. Identifying more efficient alternatives to dense matrices has enormous potential for building more compute-efficient models, as exemplified by the success of convolutional networks in the image domain. In this work, we systematically explore structured matrices as replacements for dense matrices. We show that different structures often require drastically different initialization scales and learning rates, which are crucial to performance, especially as models scale. Using insights from the Maximal Update Parameterization, we determine the optimal scaling for initialization and learning rates of these unconventional layers. Finally, we measure the scaling laws of different structures to compare how quickly their performance improves with compute. We propose a novel matrix family containing Monarch matrices, the Block Tensor-Train (BTT), which we show performs better than dense matrices for the same compute on multiple tasks. On CIFAR-10/100 with augmentation, BTT achieves exponentially lower training loss than dense when training MLPs and ViTs. BTT matches dense ViT-S/32 performance on ImageNet-1k with 3.8 times less compute and is more efficient than dense for training small GPT-2 language models.