Prior Authorization delivers safe, appropriate, and cost-effective care that is medically justified with evidence-based guidelines. However, the process often requires labor-intensive manual comparisons between patient medical records and clinical guidelines, that is both repetitive and time-consuming. Recent developments in Large Language Models (LLMs) have shown potential in addressing complex medical NLP tasks with minimal supervision. This paper explores the application of Multi-Agent System (MAS) that utilize specialized LLM agents to automate Prior Authorization task by breaking them down into simpler and manageable sub-tasks. Our study systematically investigates the effects of various prompting strategies on these agents and benchmarks the performance of different LLMs. We demonstrate that GPT-4 achieves an accuracy of 86.2% in predicting checklist item-level judgments with evidence, and 95.6% in determining overall checklist judgment. Additionally, we explore how these agents can contribute to explainability of steps taken in the process, thereby enhancing trust and transparency in the system.

Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains. However, this utility comes with increasing concerns about privacy, as the training data may include sensitive information. To address these concerns, machine unlearning has been proposed to erase specific data samples from models. While some unlearning techniques efficiently remove data at low costs, recent research highlights vulnerabilities where malicious users could request unlearning on manipulated data to compromise the model. Despite these attacks' effectiveness, perturbed data differs from original training data, failing hash verification. Existing attacks on machine unlearning also suffer from practical limitations and require substantial additional knowledge and resources. To fill the gaps in current unlearning attacks, we introduce the Unlearning Usability Attack. This model-agnostic, unlearning-agnostic, and budget-friendly attack distills data distribution information into a small set of benign data. These data are identified as benign by automatic poisoning detection tools due to their positive impact on model training. While benign for machine learning, unlearning these data significantly degrades model information. Our evaluation demonstrates that unlearning this benign data, comprising no more than 1% of the total training data, can reduce model accuracy by up to 50%. Furthermore, our findings show that well-prepared benign data poses challenges for recent unlearning techniques, as erasing these synthetic instances demands higher resources than regular data. These insights underscore the need for future research to reconsider "data poisoning" in the context of machine unlearning.

Large Language Models (LLMs) have made significant progress in assisting users to query databases in natural language. While LLM-based techniques provide state-of-the-art results on many standard benchmarks, their performance significantly drops when applied to large enterprise databases. The reason is that these databases have a large number of tables with complex relationships that are challenging for LLMs to reason about. We analyze challenges that LLMs face in these settings and propose a new solution that combines the power of LLMs in understanding questions with automated reasoning techniques to handle complex database constraints. Based on these ideas, we have developed a new framework that outperforms state-ofthe-art techniques in zero-shot text-to-SQL on complex benchmarks.

Large language models (LLMs) are increasingly applied to clinical decision-making. However, their potential to exhibit bias poses significant risks to clinical equity. Currently, there is a lack of benchmarks that systematically evaluate such clinical bias in LLMs. While in downstream tasks, some biases of LLMs can be avoided such as by instructing the model to answer "I'm not sure...", the internal bias hidden within the model still lacks deep studies. We introduce CLIMB (shorthand for A Benchmark of Clinical Bias in Large Language Models), a pioneering comprehensive benchmark to evaluate both intrinsic (within LLMs) and extrinsic (on downstream tasks) bias in LLMs for clinical decision tasks. Notably, for intrinsic bias, we introduce a novel metric, AssocMAD, to assess the disparities of LLMs across multiple demographic groups. Additionally, we leverage counterfactual intervention to evaluate extrinsic bias in a task of clinical diagnosis prediction. Our experiments across popular and medically adapted LLMs, particularly from the Mistral and LLaMA families, unveil prevalent behaviors with both intrinsic and extrinsic bias. This work underscores the critical need to mitigate clinical bias and sets a new standard for future evaluations of LLMs' clinical bias.

The recent emergence of Medical Large Vision Language Models (Med-LVLMs) has enhanced medical diagnosis. However, current Med-LVLMs frequently encounter factual issues, often generating responses that do not align with established medical facts. Retrieval-Augmented Generation (RAG), which utilizes external knowledge, can improve the factual accuracy of these models but introduces two major challenges. First, limited retrieved contexts might not cover all necessary information, while excessive retrieval can introduce irrelevant and inaccurate references, interfering with the model's generation. Second, in cases where the model originally responds correctly, applying RAG can lead to an over-reliance on retrieved contexts, resulting in incorrect answers. To address these issues, we propose RULE, which consists of two components. First, we introduce a provably effective strategy for controlling factuality risk through the calibrated selection of the number of retrieved contexts. Second, based on samples where over-reliance on retrieved contexts led to errors, we curate a preference dataset to fine-tune the model, balancing its dependence on inherent knowledge and retrieved contexts for generation. We demonstrate the effectiveness of RULE on three medical VQA datasets, achieving an average improvement of 20.8% in factual accuracy. We publicly release our benchmark and code in https://github.com/richard-peng-xia/RULE.

Converting different modalities into general text, serving as input prompts for large language models (LLMs), is a common method to align multimodal models when there is limited pairwise data. This text-centric approach leverages the unique properties of text as a modality space, transforming diverse inputs into a unified textual representation. This enables downstream models to effectively interpret various modal inputs. This study assesses the quality and robustness of multimodal representations in the presence of missing entries, noise, or absent modalities, revealing that current text-centric alignment methods compromise downstream robustness. To address this issue, we propose a new text-centric approach that achieves superior robustness compared to previous methods across various modalities in different settings. Our findings highlight the potential of this approach to enhance the robustness and adaptability of multimodal representations, offering a promising solution for dynamic and real-world applications.

Large language models (LLMs) have shown substantial progress in natural language understanding and generation, proving valuable especially in the medical field. Despite advancements, challenges persist due to the complexity and diversity inherent in medical tasks, which can be categorized as knowledge-intensive tasks and alignment-required tasks. Previous approaches either ignore the latter task or focus on a minority of tasks and hence lose generalization. To address these drawbacks, we propose a progressive fine-tuning pipeline. This pipeline employs a Knowledge Aggregator and a Noise aggregator to encode diverse knowledge in the first stage and filter out detrimental information. In the second stage, we drop the Noise Aggregator to avoid the interference of suboptimal representation and leverage an additional alignment module optimized towards an orthogonal direction to the knowledge space to mitigate knowledge forgetting. Based on this two-stage paradigm, we proposed a Medical LLM through decoupling Clinical Alignment and Knowledge Aggregation (MedCare), which is designed to achieve state-of-the-art (SOTA) performance on over 20 medical tasks, as well as SOTA results on specific medical alignment tasks. Various model sizes of MedCare (1.8B, 7B, 14B) all demonstrate significant improvements over existing models with similar model sizes.

Unit testing is crucial in software engineering for ensuring quality. However, it's not widely used in parallel and high-performance computing software, particularly scientific applications, due to their smaller, diverse user base and complex logic. These factors make unit testing challenging and expensive, as it requires specialized knowledge and existing automated tools are often ineffective. To address this, we propose an automated method for generating unit tests for such software, considering their unique features like complex logic and parallel processing. Recently, large language models (LLMs) have shown promise in coding and testing. We explored the capabilities of Davinci (text-davinci-002) and ChatGPT (gpt-3.5-turbo) in creating unit tests for C++ parallel programs. Our results show that LLMs can generate mostly correct and comprehensive unit tests, although they have some limitations, such as repetitive assertions and blank test cases.

Recent work targeting large language models (LLMs) for code generation demonstrated that increasing the amount of training data through synthetic code generation often leads to exceptional performance. In this paper we explore data pruning methods aimed at enhancing the efficiency of model training specifically for code LLMs. We present techniques that integrate various clustering and pruning metrics to selectively reduce training data without compromising the accuracy and functionality of the generated code. We observe significant redundancies in synthetic training data generation, where our experiments demonstrate that benchmark performance can be largely preserved by training on only 10% of the data. Moreover, we observe consistent improvements in benchmark results through moderate pruning of the training data. Our experiments show that these pruning strategies not only reduce the computational resources needed but also enhance the overall quality code generation.

Perhaps unsurprisingly, July 4th was a quiet day for news, but we've still got editorials on e-ink writing, the most-delayed video game ever and more bad news from the makers of ChatGPT. Earlier this week, engineer and Swift developer Pedro José Pereira Vieito dug into OpenAI's Mac ChatGPT app and found that it was storing user conversations locally in plain text, rather than encrypting them. Because that app is only available from OpenAI's website, and since it's not available on the App Store, it doesn't have to follow Apple's sandboxing requirements. OpenAI released an update that added encryption to locally stored chats. Then, more bad news stemmed from issues in 2023. Last spring, a hacker obtained information about OpenAI after illicitly accessing the company's internal messaging systems.