The consequences of a healthcare data breach can be devastating for the patients, providers, and payers. The average financial impact of a data breach in recent months has been estimated to be close to USD 10 million. This is especially significant for healthcare organizations in India that are managing rapid digitization while still establishing data governance procedures that align with the letter and spirit of the law. Computer-based systems for de-identification of personal information are vulnerable to data drift, often rendering them ineffective in cross-institution settings. Therefore, a rigorous assessment of existing de-identification against local health datasets is imperative to support the safe adoption of digital health initiatives in India. Using a small set of de-identified patient discharge summaries provided by an Indian healthcare institution, in this paper, we report the nominal performance of de-identification algorithms (based on language models) trained on publicly available non-Indian datasets, pointing towards a lack of cross-institutional generalization. Similarly, experimentation with off-the-shelf de-identification systems reveals potential risks associated with the approach. To overcome data scarcity, we explore generating synthetic clinical reports (using publicly available and Indian summaries) by performing in-context learning over Large Language Models (LLMs). Our experiments demonstrate the use of generated reports as an effective strategy for creating high-performing de-identification systems with good generalization capabilities.

The integration of artificial intelligence (AI) chatbots into higher education marks a shift towards a new generation of pedagogical tools, mirroring the arrival of milestones like the internet. With the launch of ChatGPT-4 Turbo in November 2023, we developed a ChatGPT-based teaching application (https://chat.openai.com/g/g-1imx1py4K-chatge-medical-imaging) and integrated it into our undergraduate medical imaging course in the Spring 2024 semester. This study investigates the use of ChatGPT throughout a semester-long trial, providing insights into students' engagement, perception, and the overall educational effectiveness of the technology. We systematically collected and analyzed data concerning students' interaction with ChatGPT, focusing on their attitudes, concerns, and usage patterns. The findings indicate that ChatGPT offers significant advantages such as improved information access and increased interactivity, but its adoption is accompanied by concerns about the accuracy of the information provided and the necessity for well-defined guidelines to optimize its use.

This study explores real-world human interactions with large language models (LLMs) in diverse, unconstrained settings in contrast to most prior research focusing on ethically trimmed models like ChatGPT for specific tasks. We aim to understand the originator of toxicity. Our findings show that although LLMs are rightfully accused of providing toxic content, it is mostly demanded or at least provoked by humans who actively seek such content. Our manual analysis of hundreds of conversations judged as toxic by APIs commercial vendors, also raises questions with respect to current practices of what user requests are refused to answer. Furthermore, we conjecture based on multiple empirical indicators that humans exhibit a change of their mental model, switching from the mindset of interacting with a machine more towards interacting with a human.

Existing text-to-video diffusion models rely solely on text-only encoders for their pretraining. This limitation stems from the absence of large-scale multimodal prompt video datasets, resulting in a lack of visual grounding and restricting their versatility and application in multimodal integration. To address this, we construct a large-scale multimodal prompt dataset by employing retrieval methods to pair in-context examples with the given text prompts and then utilize a two-stage training strategy to enable diverse video generation tasks within the same model. In the first stage, we propose a multimodal conditional video generation framework for pretraining on these augmented datasets, establishing a foundational model for grounded video generation. Secondly, we finetune the model from the first stage on three video generation tasks, incorporating multi-modal instructions. This process further refines the model's ability to handle diverse inputs and tasks, ensuring seamless integration of multi-modal information. After this two-stage train-ing process, VIMI demonstrates multimodal understanding capabilities, producing contextually rich and personalized videos grounded in the provided inputs, as shown in Figure 1. Compared to previous visual grounded video generation methods, VIMI can synthesize consistent and temporally coherent videos with large motion while retaining the semantic control. Lastly, VIMI also achieves state-of-the-art text-to-video generation results on UCF101 benchmark.

It is desirable to coarsely classify short scientific texts, such as grant or publication abstracts, for strategic insight or research portfolio management. These texts efficiently transmit dense information to experts possessing a rich body of knowledge to aid interpretation. Yet this task is remarkably difficult to automate because of brevity and the absence of context. To address this gap, we have developed a novel approach to generate and appropriately assign coarse domain-specific labels. We show that a Large Language Model (LLM) can provide metadata essential to the task, in a process akin to the augmentation of supplemental knowledge representing human intuition, and propose a workflow. As a pilot study, we use a corpus of award abstracts from the National Aeronautics and Space Administration (NASA). We develop new assessment tools in concert with established performance metrics.

Large language models (LLMs) sometimes exhibit dangerous unintended behaviors. Finding and fixing these is challenging because the attack surface is massive -- it is not tractable to exhaustively search for all possible inputs that may elicit such behavior. One specific and particularly challenging case is that if data-poisoning-injected trojans, since there is no way to know what they are to search for them. To our knowledge, there is no generally applicable method to unlearn unknown trojans injected during pre-training. This work seeks to provide a general purpose recipe (filters) and a specific implementation (LoRA) filters that work in practice on small to medium sized models. The focus is primarily empirical, though some perplexing behavior opens the door to the fundamental question of how LLMs store and process information. Not unexpectedly, we find that our filters work best on the residual stream and the latest layers.

Mobile applications (Apps) could expose children to inappropriate themes such as sexual content, violence, and drug use. Maturity rating offers a quick and effective method for potential users, particularly guardians, to assess the maturity levels of apps. Determining accurate maturity ratings for mobile apps is essential to protect children's health in today's saturated digital marketplace. Existing approaches to maturity rating are either inaccurate (e.g., self-reported rating by developers) or costly (e.g., manual examination). In the literature, there are few text-mining-based approaches to maturity rating. However, each app typically involves multiple modalities, namely app description in the text, and screenshots in the image. In this paper, we present a framework for determining app maturity levels that utilize multimodal large language models (MLLMs), specifically ChatGPT-4 Vision. Powered by Chain-of-Thought (CoT) reasoning, our framework systematically leverages ChatGPT-4 to process multimodal app data (i.e., textual descriptions and screenshots) and guide the MLLM model through a step-by-step reasoning pathway from initial content analysis to final maturity rating determination. As a result, through explicitly incorporating CoT reasoning, our framework enables ChatGPT to understand better and apply maturity policies to facilitate maturity rating. Experimental results indicate that the proposed method outperforms all baseline models and other fusion strategies.

Despite the wealth of single-cell multi-omics data, it remains challenging to predict the consequences of novel genetic and chemical perturbations in the human body. It requires knowledge of molecular interactions at all biological levels, encompassing disease models and humans. Current machine learning methods primarily establish statistical correlations between genotypes and phenotypes but struggle to identify physiologically significant causal factors, limiting their predictive power. Key challenges in predictive modeling include scarcity of labeled data, generalization across different domains, and disentangling causation from correlation. In light of recent advances in multi-omics data integration, we propose a new artificial intelligence (AI)-powered biology-inspired multi-scale modeling framework to tackle these issues. This framework will integrate multi-omics data across biological levels, organism hierarchies, and species to predict causal genotype-environment-phenotype relationships under various conditions. AI models inspired by biology may identify novel molecular targets, biomarkers, pharmaceutical agents, and personalized medicines for presently unmet medical needs.

Large language models (LLMs) are increasingly being used to synthesize and reason about source code. However, the static nature of these models' knowledge does not reflect the fact that libraries and API functions they invoke are continuously evolving, with functionality being added or changing. While numerous benchmarks evaluate how LLMs can generate code, no prior work has studied how an LLMs' knowledge about code API functions can be updated. To fill this gap, we present CodeUpdateArena, a benchmark for knowledge editing in the code domain. An instance in our benchmark consists of a synthetic API function update paired with a program synthesis example that uses the updated functionality; our goal is to update an LLM to be able to solve this program synthesis example without providing documentation of the update at inference time. Compared to knowledge editing for facts encoded in text, success here is more challenging: a code LLM must correctly reason about the semantics of the modified function rather than just reproduce its syntax. Our dataset is constructed by first prompting GPT-4 to generate atomic and executable function updates. Then, for each update, we generate program synthesis examples whose code solutions are prone to use the update. Our benchmark covers updates of various types to 54 functions from seven diverse Python packages, with a total of 670 program synthesis examples. Our experiments show that prepending documentation of the update to open-source code LLMs (i.e., DeepSeek, CodeLlama) does not allow them to incorporate changes for problem solving, and existing knowledge editing techniques also have substantial room for improvement. We hope our benchmark will inspire new methods for knowledge updating in code LLMs.

The rapid advancements in Large Language Models (LLMs) have opened new avenues for automating complex tasks in AI research. This paper investigates the efficacy of different LLMs-Mistral 7B, Llama-2, GPT-4-Turbo and GPT-4.o in extracting leaderboard information from empirical AI research articles. We explore three types of contextual inputs to the models: DocTAET (Document Title, Abstract, Experimental Setup, and Tabular Information), DocREC (Results, Experiments, and Conclusions), and DocFULL (entire document). Our comprehensive study evaluates the performance of these models in generating (Task, Dataset, Metric, Score) quadruples from research papers. The findings reveal significant insights into the strengths and limitations of each model and context type, providing valuable guidance for future AI research automation efforts.