Synthetic Data Generation for Improving Clinical Documentation
Accurate and comprehensive clinical documentation is crucial for delivering high-quality healthcare,
facilitating effective communication among providers, and ensuring compliance with regulatory requirements.
Through extensive experiments on a large dataset of anonymized clinical transcripts, we demonstrate the effectiveness
of our approach in generating high-quality synthetic transcripts that closely resemble real-world data.
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite As: arXiv:2406.06569 [cs.CL]
Journal: International Journal of Innovative Science and Research Technology: Vol. 9 (2024): No. 5, 1553-1566
Read paper
A Cost-Effective Approach of Classifying Financial Documents with Vector Sampling using Multi-modal Embedding Models
Accurate classification of multi-modal financial documents, containing text, tables, charts, and images, is crucial but challenging. Traditional text-based approaches often fail to capture the complex multi-modal nature of these documents. We propose FinEmbedDiff, a cost-effective vector sampling method that leverages pre-trained multi-modal embedding models to classify financial documents. Our approach generates multi-modal embedding vectors for documents, and compares new documents with pre-computed class embeddings using vector similarity measures.
Subjects: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
Cite As: arXiv:2406.01618 [cs.IR]
Journal: International Research Journal of Modernization in Engineering Technology and Science: Vol. 06 (2024): No. 5, 6142-6152
Read paper
Synergizing Unsupervised and Supervised Learning: A Hybrid Approach for Accurate Natural Language Task Modeling
While supervised learning models have shown remarkable performance in various natural language processing (NLP) tasks, their success heavily relies on the availability of large-scale labeled datasets, which can be costly and time-consuming to obtain. This paper presents a novel hybrid approach that synergizes unsupervised and supervised learning to improve the accuracy of NLP task modeling.
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)
Cite As: arXiv:2406.01096 [cs.CL]
Journal: International Journal of Innovative Science and Research Technology: Vol. 9 (2024): No. 5, 1499-1508
Read paper
LLMs can be highly effective in healthcare
Comprehensive clinical documentation is crucial for effective healthcare delivery, yet it poses a significant burden on healthcare professionals, leading to burnout, increased medical errors, and compromised patient safety.
We present a case study demonstrating the application of natural language processing (NLP) and automatic speech recognition (ASR) technologies to transcribe patient-clinician interactions, coupled with advanced prompting techniques to generate draft clinical notes using large language models (LLMs).
Subjects: Artificial Intelligence (cs.AI)
Cite As: arXiv:2405.18346 [cs.AI]
Journal: International Journal of Innovative Science and Research Technology: Vol. 9 (2024): No. 5, 994-1008
Read paper
Data extraction using multi-modal LLMs
Multi-modal large language models (LLMs) have shown remarkable performance in various natural language processing tasks, including data extraction from documents. However, the accuracy of these models can be significantly affected by document in-plane rotation, also known as skew, a common issue in real-world scenarios for scanned documents.
This study investigates the impact of document skew on the data extraction accuracy of three state-of-the-art multi-modal LLMs: Anthropic Claude V3 Sonnet, GPT-4-Turbo, and Llava:v1.6. We focus on extracting specific entities from synthetically generated sample documents with varying degrees of skewness.
Subjects: Computation and Language (cs.CL); Information Retrieval (cs.IR)
Cite As: arXiv:2406.10295 [cs.CL]
Journal: Journal of Artificial Intelligence Research: Vol. 4 (2024): No. 1, 176-195
Read paper
Context aware grounding can improve LLM's fidelity
As Large Language Models (LLMs) become increasingly sophisticated and ubiquitous in natural language processing (NLP) applications, ensuring their robustness, trustworthiness, and alignment with human values has become a critical challenge. This paper presents a novel framework for contextual grounding in textual models, with a particular emphasis on the Context Representation stage.
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite As: arXiv:2408.04023 [cs.CL]
Journal: World Journal of Advanced Engineering Technology and Sciences, 2023, 10(2), 283-296
Read paper
Trust, safety, and ethics in development of LLMs
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite As: https://doi.org/10.55662/JST.2023.4605
Journal: https://thesciencebrigade.com/jst/article/view/245/237
Read paper