Retrieval-Augmented Generation (RAG) systems have emerged as a powerful process for allowing large language models (LLMs) to retrieve relevant information to use as source material during text generation. A critical yet under-explored component of these systems is the granularity at which source documents are segmented into retrievable chunks. The size of these chunks has the potential to significantly influence generation quality, contextual correctness, retrieval precision, and computational efficiency. Despite its importance, chunk size is often selected without proper evaluation of its impact on generation quality. Smaller chunks, such as individual sentences, may allow for precise retrieval by narrowing the focus of each chunk. However, they contain less information, which may limit the model's ability to generate coherent responses. Larger chunks, such as entire chapters, contain lots of broad information that may improve correctness, but also introduce additional noise and increase computational cost. Because larger chunks contain more information, the number of chunks returned to the model must also be considered. This paper evaluates how chunk size, along with the number of retrieved segments, influences generation quality and retrieval effectiveness. By comparing these configurations, this study seeks to better understand how document segmentation affects the performance and efficiency of Retrieval-Augmented Generation systems. segmentation affects the performance and efficiency of Retrieval-Augmented Generation systems.
Standard Retrieval-Augmented Generation pipelines rank retrieved documents by semantic similarity alone, without accounting for source provenance or credibility. This work evaluates a simple and interpretable modification to RAG retrieval ranking that incorporates domain-informed source reliability priors. Each document is assigned a prior lambda(s) based on its source type, and retrieval scores are reweighted using score(q, d) = sim(q, d) * lambda(s). The framework is evaluated against a similarity-only baseline on a 120-document health-domain corpus. In this controlled setting, source-aware reranking improves Precision@5 from 0.48 to 0.72 and reduces average adversarial document retrieval under the evaluated threat model, where low-credibility sources are identifiable via metadata. All experiments were executed on Rosie, the high-performance computing cluster at the Milwaukee School of Engineering, which provided the GPU-accelerated infrastructure necessary to run the full experimental pipeline reliably and reproducibly. These results suggest a potential mitigation strategy for source quality degradation in RAG pipelines, within the limits of the experimental setup described.
As video content continues to expand across educational platforms, recorded lectures, and live-streamed entertainment, the need for efficient and structured analysis of long-form footage has increased \cite{1}. Although many existing AI programs provide high-level video summaries based on AI-generated transcripts \cite{2,3,4,5}, these approaches are often limited to coarse overviews and lack detailed analysis of a video's structure, thematic progression, and semantic relationships, all of which are required for comprehensive video analysis. This paper proposes an LLM-based video summarization framework that balances macro-level comprehension with micro-level semantic analysis \cite{6,12,13}. The first stage of the process indexes the video at a micro level by (1) analyzing the full transcript, (2) analyzing individual transcript sentences, and (3) grouping these sentences by semantic similarity using an LLM as a judge \cite{6,13}. Contextual continuity is retained during sentence-level processing by incorporating both the global transcript analysis and adjacent sentence information into each evaluation prompt. This framework establishes a foundation for video analysis tools that visualize semantic chunking and semantic matching through relevance-based heatmaps. Limitations and future expansions of the framework are also discussed.
Disc degeneration is the primary cause of low back pain, although the disc itself is not usually the source of the pain. Instead, it can lead to various clinically significant conditions that cause pain. However, there are no objective measures of the disc degeneration. Lack of objective measures of disc degeneration may sometimes cause uncertainties in treatment decisions. Currently disc degeneration is graded by visual assessment of MRI, which often leads to uncertainty and disagreements. Therefore, the objective of this study was to develop a simple, efficient, accurate, and objective diagnostic tool for assessing disc degeneration. Prospective (data acquired on site) and retrospective (data from online repository). Lumbar spine MRI data from 277 participants are used. 208 of those were from an online repository and 69 were from our site. 3.0T; T2 weighted 2D and 3D fast spin echo pulse sequences. A fully automated method is implemented where selected radiomics features are calculated from T2 weighted MRI and used for classification of the disc degeneration grade. Binary disc masks are generated using nnU-Net and radiomics features are extracted using Pyradiomics. Optimal preprocessing approaches are explored to obtain reliable feature calculations from repeated scans. Several advanced decision tree classification methods were also tested. F1 accuracy score, Area Under the Curve, confidence interval. XGBoost was in good agreement with the rater and the important features used in classification were in accord with expected changes in discs. Automated evaluation of disc degeneration streamlines the physician’s workflow and reduces uncertainties. Using radiomics features enables explainability and provides simple and robust training for machine learning approaches. 2 3
In this recorded interview, Dr. Nadya Shalamova shares her personal reflections about being a women in Siberia during the Soviet period and about Siberian Soviet matriculture. Transcript available (see PDF). LINK TO VIDEO INTERVIEW: Personal Reflections on the Matriculture of the Siberian Soviet Union.
