While holding great promise for improving and facilitating healthcare, large language models (LLMs) struggle to produce up-to-date responses on evolving topics due to outdated knowledge or hallucination. Retrieval-augmented generation (RAG) is a pivotal innovation that improves the accuracy and relevance of LLM responses by integrating LLMs with a search engine and external sources of knowledge. However, the quality of RAG responses can be largely impacted by the rank and density of key information in the retrieval results, such as the "lost-in-the-middle" problem. In this work, we aim to improve the robustness and reliability of the RAG workflow in the medical domain. Specifically, we propose a map-reduce strategy, BriefContext, to combat the "lost-in-the-middle" issue without modifying the model weights. We demonstrated the advantage of the workflow with various LLM backbones and on multiple QA datasets. This method promises to improve the safety and reliability of LLMs deployed in healthcare domains.

Human tutoring interventions play a crucial role in supporting student learning, improving academic performance, and promoting personal growth. This paper focuses on analyzing mathematics tutoring discourse using talk moves - a framework of dialogue acts grounded in Accountable Talk theory. However, scaling the collection, annotation, and analysis of extensive tutoring dialogues to develop machine learning models is a challenging and resource-intensive task. To address this, we present SAGA22, a compact dataset, and explore various modeling strategies, including dialogue context, speaker information, pretraining datasets, and further fine-tuning. By leveraging existing datasets and models designed for classroom teaching, our results demonstrate that supplementary pretraining on classroom data enhances model performance in tutoring settings, particularly when incorporating longer context and speaker information. Additionally, we conduct extensive ablation studies to underscore the challenges in talk move modeling.

In this work, we introduce the task of life-long personalization of large language models. While recent mainstream efforts in the LLM community mainly focus on scaling data and compute for improved capabilities of LLMs, we argue that it is also very important to enable LLM systems, or language agents, to continuously adapt to the diverse and ever-changing profiles of every distinct user and provide up-to-date personalized assistance. We provide a clear task formulation and introduce a simple, general, effective, and scalable framework for life-long personalization of LLM systems and language agents. To facilitate future research on LLM personalization, we also introduce methods to synthesize realistic benchmarks and robust evaluation metrics. We will release all codes and data for building and benchmarking life-long personalized LLM systems.

Radiology reports, designed for efficient communication between medical experts, often remain incomprehensible to patients. This inaccessibility could potentially lead to anxiety, decreased engagement in treatment decisions, and poorer health outcomes, undermining patient-centered care. We present ReXplain (Radiology eXplanation), an innovative AI-driven system that translates radiology findings into patient-friendly video reports. ReXplain uniquely integrates a large language model for medical text simplification and text-anatomy association, an image segmentation model for anatomical region identification, and an avatar generation tool for engaging interface visualization. ReXplain enables producing comprehensive explanations with plain language, highlighted imagery, and 3D organ renderings in the form of video reports. To evaluate the utility of ReXplain-generated explanations, we conducted two rounds of user feedback collection from six board-certified radiologists. The results of this proof-of-concept study indicate that ReXplain could accurately deliver radiological information and effectively simulate one-on-one consultation, shedding light on enhancing patient-centered radiology with potential clinical usage. This work demonstrates a new paradigm in AI-assisted medical communication, potentially improving patient engagement and satisfaction in radiology care, and opens new avenues for research in multimodal medical communication.

If you've been waiting patiently to try ChatGPT Search, you won't have to wait much longer. After rolling out to paid subscribers this fall, OpenAI announced Monday it would make the tool available to everyone, no Plus or Pro membership necessary, "over the coming months." At that point, all you need before you can start using ChatGPT Search is an OpenAI account. Once you're logged in, and if your query calls for it, ChatGPT will automatically search the web for the latest information to answer your question. You can also force it to search the web, thanks to a handy new icon located right in the prompt bar.

It has been a typically chaotic 12 months for Elon Musk. The world's richest person has been pulled from one direction to another in the running of his many companies – with mixed results. How this moment for AI will change society forever (and how it won't) There is no doubt that the latest advances in artificial intelligence from OpenAI, Google, Baidu and others are more impressive than what came before, but are we in just another bubble of AI hype?

We propose LLM-DaaS, a novel Drone-as-a-Service (DaaS) framework that leverages Large Language Models (LLMs) to transform free-text user requests into structured, actionable DaaS operation tasks. Our approach addresses the key challenge of interpreting and structuring natural language input to automate drone service operations under uncertain conditions. The system is composed of three main components: free-text request processing, structured request generation, and dynamic DaaS selection and composition. First, we fine-tune different LLM models such as Phi-3.5, LLaMA-3.2 7b and Gemma 2b on a dataset of text user requests mapped to structured DaaS requests. Users interact with our model in a free conversational style, discussing package delivery requests, while the fine-tuned LLM extracts DaaS metadata such as delivery time, source and destination locations, and package weight. The DaaS service selection model is designed to select the best available drone capable of delivering the requested package from the delivery point to the nearest optimal destination. Additionally, the DaaS composition model composes a service from a set of the best available drones to deliver the package from the source to the final destination. Second, the system integrates real-time weather data to optimize drone route planning and scheduling, ensuring safe and efficient operations. Simulations demonstrate the system's ability to significantly improve task accuracy, operational efficiency, and establish LLM-DaaS as a robust solution for DaaS operations in uncertain environments.

Logs are critical resources that record events, activities, or messages produced by software applications, operating systems, servers, and network devices. However, consolidating the heterogeneous logs and cross-referencing them is challenging and complicated. Manually analyzing the log data is time-consuming and prone to errors. LogBabylon is a centralized log data consolidating solution that leverages Large Language Models (LLMs) integrated with Retrieval-Augmented Generation (RAG) technology. LogBabylon interprets the log data in a human-readable way and adds insight analysis of the system performance and anomaly alerts. It provides a paramount view of the system landscape, enabling proactive management and rapid incident response. LogBabylon consolidates diverse log sources and enhances the extracted information's accuracy and relevancy. This facilitates a deeper understanding of log data, supporting more effective decision-making and operational efficiency. Furthermore, LogBabylon streamlines the log analysis process, significantly reducing the time and effort required to interpret complex datasets. Its capabilities extend to generating context-aware insights, offering an invaluable tool for continuous monitoring, performance optimization, and security assurance in dynamic computing environments.

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge surge in generative audio, speech, and music models that utilize discrete audio tokens derived from neural compression algorithms, e.g. ENCODEC. However, one of the major drawbacks of this approach is handling the context length. It blows up for high-fidelity generative architecture if one has to account for all the audio contents at various frequencies for the next token prediction. By combining continuous audio representation like the spectrogram and discrete acoustic tokens, we retain the best of both worlds: Have all the information needed from the audio at a specific time instance in a single token, yet allow LLM to predict the future token to allow for sampling and other benefits discrete space provides. We show how our architecture improves the perplexity and negative log-likelihood scores for the next token prediction compared to a token-based LLM for speech and music.

Large Language Models (LLMs) have shown significant potential as judges for Machine Translation (MT) quality assessment, providing both scores and fine-grained feedback. Although approaches such as GEMBA-MQM have shown state-of-the-art performance on reference-free evaluation, the predicted errors do not align well with those annotated by human, limiting their interpretability as feedback signals. To enhance the quality of error annotations predicted by LLM evaluators, we introduce a universal and training-free framework, $\textbf{MQM-APE}$, based on the idea of filtering out non-impactful errors by Automatically Post-Editing (APE) the original translation based on each error, leaving only those errors that contribute to quality improvement. Specifically, we prompt the LLM to act as 1) $\textit{evaluator}$ to provide error annotations, 2) $\textit{post-editor}$ to determine whether errors impact quality improvement and 3) $\textit{pairwise quality verifier}$ as the error filter. Experiments show that our approach consistently improves both the reliability and quality of error spans against GEMBA-MQM, across eight LLMs in both high- and low-resource languages. Orthogonal to trained approaches, MQM-APE complements translation-specific evaluators such as Tower, highlighting its broad applicability. Further analysis confirms the effectiveness of each module and offers valuable insights into evaluator design and LLMs selection.