13197 research outputs found
Sort by
Smart Rehabilitation for Augmenting Therapists’ Skills: A Mixed Reality System for Simulating AI-Generated Patient-Specific Impaired Walking Motions and an Assistive Robotic Walker
Full text link奈良先端科学技術大学院大学修士（工学）master thesi
Balancing Embedding Spectrum for Recommendation
Full text linkModern recommender systems heavily rely on high-quality representations learned from high-dimensional sparse data. While significant efforts have been invested in designing powerful algorithms for extracting user preferences, the factors contributing to good representations have remained relatively unexplored. In this work, we shed light on an issue in the existing pairwise learning paradigm (i.e., embedding collapse), that the representations tend to span a subspace of the whole embedding space, leading to a suboptimal solution and reducing the model capacity. Specifically, we show that alignment of positive pairs is equivalent to a low-pass filter causing users and items to collapse to a constant vector. While negative sampling can partially mitigate this issue by acting as a high-pass filter to balance the spectrum, leading to an incomplete collapse.To tackle this issue, we present a novel learning paradigm DirectSpec, which directly optimizes the spectrum distribution to ensure that users and items effectively span the entire embedding space. We demonstrate that many self-supervised learning algorithms without explicit negative sampling can be considered as special cases of DirectSpec. Furthermore, we show that optimizing the spectrum inappropriately could also be detrimental to data representation, where the key lies in a dynamic balance between alignment of positive pairs and spectrum balancing. Finally, we propose an enhanced and practical implementation DirectSpec+ to balance the embedding spectrum more adaptively and effectively. We implement DirectSpec+ on two popular recommender models: matrix factorization and LightGCN. Our experimental results demonstrate its effectiveness and efficiency over competitive baselines.journal articl
Evaluating and Enhancing Japanese Large Language Models for Genetic Counseling Support: Comparative Study of Domain Adaptation and the Development of an Expert-Evaluated Dataset
No full textBackground: Advances in genetics have underscored a strong association between genetic factors and health outcomes, leading to an increased demand for genetic counseling services. However, a shortage of qualified genetic counselors poses a significant challenge. Large language models (LLMs) have emerged as a potential solution for augmenting support in genetic counseling tasks. Despite the potential, Japanese genetic counseling LLMs (JGCLLMs) are underexplored. To advance a JGCLLM-based dialogue system for genetic counseling, effective domain adaptation methods require investigation. Objective: This study aims to evaluate the current capabilities and identify challenges in developing a JGCLLM-based dialogue system for genetic counseling. The primary focus is to assess the effectiveness of prompt engineering, retrieval-augmented generation (RAG), and instruction tuning within the context of genetic counseling. Furthermore, we will establish an experts-evaluated dataset of responses generated by LLMs adapted to Japanese genetic counseling for the future development of JGCLLMs. Methods: Two primary datasets were used in this study: (1) a question-answer (QA) dataset for LLM adaptation and (2) a genetic counseling question dataset for evaluation. The QA dataset included 899 QA pairs covering medical and genetic counseling topics, while the evaluation dataset contained 120 curated questions across 6 genetic counseling categories. Three enhancement techniques of LLMs---instruction tuning, RAG, and prompt engineering---were applied to a lightweight Japanese LLM to enhance its ability for genetic counseling. The performance of the adapted LLM was evaluated on the 120-question dataset by 2 certified genetic counselors and 1 ophthalmologist (SK, YU, and AY). Evaluation focused on four metrics: (1) inappropriateness of information, (2) sufficiency of information, (3) severity of harm, and (4) alignment with medical consensus. Results: The evaluation by certified genetic counselors and an ophthalmologist revealed varied outcomes across different methods. RAG showed potential, particularly in enhancing critical aspects of genetic counseling. In contrast, instruction tuning and prompt engineering produced less favorable outcomes. This evaluation process facilitated the creation an expert-evaluated dataset of responses generated by LLMs adapted with different combinations of these methods. Error analysis identified key ethical concerns, including inappropriate promotion of prenatal testing, criticism of relatives, and inaccurate probability statements. Conclusions: RAG demonstrated notable improvements across all evaluation metrics, suggesting potential for further enhancement through the expansion of RAG data. The expert-evaluated dataset developed in this study provides valuable insights for future optimization efforts. However, the ethical issues observed in JGCLLM responses underscore the critical need for ongoing refinement and thorough ethical evaluation before these systems can be implemented in health care settings.journal articl
Epigenetic regulation of neural stem cell aging in the mouse hippocampus by Setd8 downregulation
Full text linkNeural stem cells (NSCs) in the mammalian brain decline rapidly with age, leading to impairment of hippocampal memory function in later life. However, the relationship between epigenetic remodeling and transcriptional regulation that compromises hippocampal NSC activity during the early stage of chronological aging remains unclear. Here, we performed single-cell RNA sequencing (scRNA-seq) and single-cell ATAC sequencing (scATAC-seq) on NSCs and newly generated neurons across different stages. Integrated data analysis revealed continuous alterations in the chromatin profile of hippocampal NSCs and their progeny from neonatal to mature adult stages, accompanied by consistent changes in transcriptional profiles. Further, decreased expression of Setd8, encoding the enzyme for histone H4 monomethylation at lysine 20 (H4K20me1), underlies age-related changes in mouse hippocampal NSCs. Notably, depletion of Setd8 elicits alterations in gene expression and epigenetic regulation that phenocopy age-related changes, and impairs NSC activity, leading to hippocampal memory deficits. Together, our study provides a global map of longitudinal chromatin and transcriptome changes during brain aging and identifies mechanistic insights into early-onset decline of NSC activity and hippocampal neurogenesis that precedes functional aging.journal articl
RecordTwin: Towards Creating Safe Synthetic Clinical Corpora
No full textThe scarcity of publicly available clinical corpora hinders developing and applying NLP tools in clinical research. While existing work tackles this issue by utilizing generative models to create high-quality synthetic corpora, their methods require learning from the original in-hospital clinical documents, turning them unfeasible in practice. To address this problem, we introduce RecordTwin, a novel synthetic corpus creation method designed to generate synthetic documents from anonymized clinical entities. In this method, we first extract and anonymize entities from in-hospital documents to ensure the information contained in the synthetic corpus is restricted. Then, we use a large language model to fill the context between anonymized entities. To do so, we use a small, privacy-preserving subset of the original documents to mimic their formatting and writing style. This approach only requires anonymized entities and a small subset of original documents in the generation process, making it more feasible in practice. To evaluate the synthetic corpus created with our method, we conduct a proof-of-concept study using a publicly available clinical database. Our results demonstrate that the synthetic corpus has a utility comparable to the original data and a safety advantage over baselines, highlighting the potential of RecordTwin for privacy-preserving synthetic corpus creation.conference pape
Lexical Simplification: From a Japanese Dataset to Multilingual Methods Leveraging Large Language Models and a YouTube Subtitle Corpus
Full text link奈良先端科学技術大学院大学博士（理学）doctoral thesi
Incorporating Human-interpretable Criteria into Automated Evaluation of Essay and Simultaneous Interpreting
Full text link奈良先端科学技術大学院大学博士（工学）doctoral thesi
Adaptive AR Gaming Experiences: Creating Intelligent Systems for Better Integration and Interaction of Real and Virtual World
Full text link奈良先端科学技術大学院大学博士（工学）doctoral thesi
カキテ ヨミテ ノ コドクカン ニ モトズク データセット ノ コウチク ト コドクカン ヨソク ニ カンスル ケンキュウ
Full text link奈良先端科学技術大学院大学修士（工学）master thesi