We present a comparative analysis of the parseability of structured outputs generated by small language models for open attribute-value extraction from clinical notes. We evaluate three widely used serialization formats: JSON, YAML, and XML, and find that JSON consistently yields the highest parseability. Structural robustness improves with targeted prompting and larger models, but declines for longer documents and certain note types. Our error analysis identifies recurring format-specific failure patterns. These findings offer practical guidance for selecting serialization formats and designing prompts when deploying language models in privacy-sensitive clinical settings.

This study examines the performance of Large Language Models (LLMs) in Aspect-Based Sentiment Analysis (ABSA), with a focus on implicit aspect extraction in a novel domain. Using a synthetic sports feedback dataset, we evaluate open-weight LLMs’ ability to extract aspect-polarity pairs and propose a metric to facilitate the evaluation of aspect extraction with generative models. Our findings highlight both the potential and limitations of LLMs in the ABSA task.

This study assesses the ability of machine learning to classify verses from Buddhist texts into two categories: Therigatha and Theragatha, attributed to female and male authors, respectively. It highlights the difficulties in data preprocessing and the use of Transformer-based models on Devanagari script due to limited vocabulary, demonstrating that simple statistical models can be equally effective. The research suggests areas for future exploration, provides the dataset for further study, and acknowledges existing limitations and challenges.