This work demonstrates the possibilities for improving wildfire and air quality management in the western United States by leveraging the unprecedented hourly data from NASA's TEMPO satellite mission and advances in self-supervised deep learning. Here we demonstrate the efficacy of deep learning for mapping the near real-time hourly spread of wildfire fronts and smoke plumes using an innovative self-supervised deep learning-system: successfully distinguishing smoke plumes from clouds using GOES-18 and TEMPO data, strong agreement across the smoke and fire masks generated from different sensing modalities as well as significant improvement over operational products for the same cases.

The use of Large Language Models (LLMs) in hardware design has taken off in recent years, principally through its incorporation in tools that increase chip designer productivity. There has been considerable discussion about the use of LLMs in RTL specifications of chip designs, for which the two most popular languages are Verilog and VHDL. LLMs and their use in Verilog design has received significant attention due to the higher popularity of the language, but little attention so far has been given to VHDL despite its continued popularity in the industry. There has also been little discussion about the unique needs of organizations that engage in high-performance processor design, and techniques to deploy AI solutions in these settings. In this paper, we describe our journey in developing a Large Language Model (LLM) specifically for the purpose of explaining VHDL code, a task that has particular importance in an organization with decades of experience and assets in high-performance processor design. We show how we developed test sets specific to our needs and used them for evaluating models as we performed extended pretraining (EPT) of a base LLM. Expert evaluation of the code explanations produced by the EPT model increased to 69% compared to a base model rating of 43%. We further show how we developed an LLM-as-a-judge to gauge models similar to expert evaluators. This led us to deriving and evaluating a host of new models, including an instruction-tuned version of the EPT model with an expected expert evaluator rating of 71%. Our experiments also indicate that with the potential use of newer base models, this rating can be pushed to 85% and beyond. We conclude with a discussion on further improving the quality of hardware design LLMs using exciting new developments in the Generative AI world.

While general-purpose Large Language Models (LLMs) have demonstrated remarkable proficiency across diverse natural language tasks, their inherent lack of domain-specific knowledge often renders them inadequate for specialized telecom applications, such as intricate network optimization, real-time fault diagnosis, and automated configuration management. To bridge this capability gap, we introduce TSLAM-Mini, a meticulously fine-tuned iteration of the Phi-4 Mini Instruct 4B model. TSLAM-Mini is specifically tailored for telecommunications tasks, leveraging a comprehensive dataset of 100,000 samples that span 20 consolidated and critical telecommunications categories. These categories, delineated in Section 3, encompass a wide spectrum from foundational networking principles (e.g., Network Fundamentals, IP Routing, MPLS) to advanced and emerging areas (e.g., Network Security, Automation, OSS/BSS, RAN, Mobile Core, Satellite Communications, and Ethical AI). The foundational dataset was synthesized utilizing Ne-toAI's DigiTwin platform, which facilitates the creation of high-fidelity digital replicas of network devices and environments. This approach allows for the generation of realistic network operation data, further enriched by insights from seasoned Subject Matter Experts (SMEs) and normative information extracted from pertinent Request for Comments (RFCs), ensuring profound domain relevance. The fine-tuning process employs Quantized Low-Rank Adaptation (QLoRA), a Parameter-Efficient Fine-Tuning (PEFT) technique, to optimize training efficiency and computational footprint, thereby enabling deployment on resource-constrained edge devices or embedded systems. This research endeavors to significantly enhance TSLAM-Mini's capacity to deliver precise, context-aware, and actionable responses to complex telecom challenges, thereby contributing to the paradigm of intelligent, resilient, and autonomous network management and advancing the frontier of applied LLMs in the telecommunications sector.

Population-based cancer registries (PBCRs) face a significant bottleneck in manually extracting data from unstructured pathology reports, a process crucial for tasks like tumor group assignment, which can consume 900 person-hours for approximately 100,000 reports. To address this, we introduce ELM (Ensemble of Language Models), a novel ensemble-based approach leveraging both small language models (SLMs) and large language models (LLMs). ELM utilizes six fine-tuned SLMs, where three SLMs use the top part of the pathology report and three SLMs use the bottom part. This is done to maximize report coverage. ELM requires five-out-of-six agreement for a tumor group classification. Disagreements are arbitrated by an LLM with a carefully curated prompt. Our evaluation across nineteen tumor groups demonstrates ELM achieves an average precision and recall of 0.94, outperforming single-model and ensemble-without-LLM approaches. Deployed at the British Columbia Cancer Registry, ELM demonstrates how LLMs can be successfully applied in a PBCR setting to achieve state-of-the-art results and significantly enhance operational efficiencies, saving hundreds of person-hours annually.

We present ARCAS (Automated Root Cause Analysis System), a diagnostic platform based on a Domain Specific Language (DSL) built for fast diagnostic implementation and low learning curve. Arcas is composed of a constellation of automated troubleshooting guides (Auto-TSGs) that can execute in parallel to detect issues using product telemetry and apply mitigation in near-real-time. The DSL is tailored specifically to ensure that subject matter experts can deliver highly curated and relevant Auto-TSGs in a short time without having to understand how they will interact with the rest of the diagnostic platform, thus reducing time-to-mitigate and saving crucial engineering cycles when they matter most. This contrasts with platforms like Datadog and New Relic, which primarily focus on monitoring and require manual intervention for mitigation. ARCAS uses a Large Language Model (LLM) to prioritize Auto-TSGs outputs and take appropriate actions, thus suppressing the costly requirement of understanding the general behavior of the system. We explain the key concepts behind ARCAS and demonstrate how it has been successfully used for multiple products across Azure Synapse Analytics and Microsoft Fabric Synapse Data Warehouse.

Urban blight is a problem of high interest for planning and policy making. Researchers frequently propose theories about the relationships between urban blight indicators, focusing on relationships reflecting causality. In this paper, we improve on the integration of domain knowledge in the analysis of urban blight by introducing four rules for effective modeling of causal domain knowledge. The findings of this study reveal significant deviation from causal modeling guidelines by investigating cognitive maps developed for urban blight analysis. These findings provide valuable insights that will inform future work on urban blight, ultimately enhancing our understanding of urban blight complex interactions.

With the right design [46], such interfaces could enable experts to steer the output of LLMs toward content that better aligns with the nuances and needs of their domains, and transform the role of the subject matter expert from a producer to a curator--a competent and critical judge who instructs the AI agent on what is needed, evaluates the output, and iterates on the instructions until the results are satisfactory. Instead of replacing human experts, these interfaces could help bridge human intelligence with machine intelligence to dramatically reduce the time and effort required to create content that adheres to expert tastes and standards. To realize the producer-to-curator shift and integrate domain expertise more closely into prompt engineering, we need authoring interfaces that: (i) deeply embed LLMs within existing expert workflows, augmenting content creation with carefully scaffolded interface support for prompt engineering; (ii) encourage experimentation on many prompt variations to systematically test the impact of changes in instructional wording on model output; (iii) offer mechanisms for curating prompt formulations that work well at various levels of abstraction; (iv) integrate generation into the publishing workflow. However, designing authoring interfaces that support experts across all four fronts is difficult as LLMs pose unique usability challenges tied to high metacognitive demands during prompt construction [45], and users can struggle to get the models to integrate well with their existing workflow as even small perturbations such as adding a space at the end of a prompt can cause the LLM to change its output [37]. For domain experts who aren't AI specialists, recent literature on prompt engineering has also highlighted how designing effective prompts can be surprisingly difficult for non-AI experts [8, 51].

Clients wishing to implement generative AI in the domain of IT Support and AIOps face two critical issues: domain coverage and model size constraints due to model choice limitations. Clients might choose to not use larger proprietary models such as GPT-4 due to cost and privacy concerns and so are limited to smaller models with potentially less domain coverage that do not generalize to the client's domain. Retrieval augmented generation is a common solution that addresses both of these issues: a retrieval system first retrieves the necessary domain knowledge which a smaller generative model leverages as context for generation. We present a system developed for a client in the IT Support domain for support case solution recommendation that combines retrieval augmented generation (RAG) for answer generation with an encoder-only model for classification and a generative large language model for query generation. We cover architecture details, data collection and annotation, development journey and preliminary validations, expected final deployment process and evaluation plans, and finally lessons learned.

Blockers can take a tiny task and stretch it over days or weeks. Taking a moment at the beginning of a project to look for and prevent possible blockers can improve productivity. These examples of personal, team, and organizational levels show how gathering the right information and performing preflight checks can save hours of wasted time later. Two IT workers--Andrew and Bertie (not their real names)--were assigned the same task. While this task should have taken about an hour of hands-on keyboard work, it took Andrew four days. Andrew began the task one sunny Monday morning. Work went well until he hit a speed bump and needed to ask the requester (who we will call Roger) a question. Andrew tried to find him on the company chat system, only to learn Roger was out of the office. Andrew sent an email instead.

Thematic analysis and other variants of inductive coding are widely used qualitative analytic methods within empirical legal studies (ELS). We propose a novel framework facilitating effective collaboration of a legal expert with a large language model (LLM) for generating initial codes (phase 2 of thematic analysis), searching for themes (phase 3), and classifying the data in terms of the themes (to kick-start phase 4). We employed the framework for an analysis of a dataset (n = 785) of facts descriptions from criminal court opinions regarding thefts. The goal of the analysis was to discover classes of typical thefts. Our results show that the LLM, namely OpenAI's GPT-4, generated reasonable initial codes, and it was capable of improving the quality of the codes based on expert feedback. They also suggest that the model performed well in zero-shot classification of facts descriptions in terms of the themes. Finally, the themes autonomously discovered by the LLM appear to map fairly well to the themes arrived at by legal experts. These findings can be leveraged by legal researchers to guide their decisions in integrating LLMs into their thematic analyses, as well as other inductive coding projects.