This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs). Our two-step approach involves data point summarization and hidden state extraction. Initially, data is condensed via summarization using an LLM, reducing complexity and highlighting essential information in sentences. Subsequently, the summarization sentences are fed through another LLM to extract hidden states, serving as compact, feature-rich representations. This approach leverages the advanced comprehension and generative capabilities of LLMs, offering a scalable and efficient strategy for similarity identification across diverse datasets. We demonstrate the effectiveness of our method in identifying similar data points on multiple datasets. Additionally, our approach enables non-technical domain experts, such as fraud investigators or marketing operators, to quickly identify similar data points tailored to specific scenarios, demonstrating its utility in practical applications. In general, our results open new avenues for leveraging LLMs in data analysis across various domains
Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models
FocusMed: A Large Language Model-based Framework for Enhancing Medical Question Summarization with Focus Identification
1 College of Computer Science;Technology, Dalian University of Technology, Dalian, China;2 Cancer Hospital of Dalian University of Technology, Liaoning Cancer Hospital \& Institute, Shenyang, China
The Daily Dose: Workflow-Integrated Large Language Model Automation for Clinical Summarization and Trial Identification in Radiation Oncology
Department of Radiation Oncology, Mayo Clinic, Phoenix, AZ, United States(辐射肿瘤科,梅奥诊所,凤凰城,亚利桑那州,美国);Department of Radiation Oncology, Mayo Clinic, Rochester, MN, United States(辐射肿瘤科,梅奥诊所,罗切斯特,明尼苏达州,美国);Division of Radiation Oncology, IEO, European Institute of Oncology, IRCCS, Milan, Italy(放射肿瘤学部,IEO,欧洲肿瘤研究所,IRCCS,米兰,意大利)
KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report Summarization
Korea University(高丽大学);Microsoft Research Asia(微软亚洲研究院);KAIST AI(韩国科学技术院人工智能学院);Beihang University(北京航空航天大学);Centre for Perceptual and Interactive Intelligence(感知与交互智能研究中心);AIGEN Sciences Inc.(AIGEN科学公司)
提出面向胸部 X 光的预训练视觉-语言模型 CheXOFA,通过多任务统一、跨领域迁移、集成与事实校准提升放射学报告摘要性能,并在 RadSum23 隐藏测试集取得第一名。
Towards an Automated Multimodal Approach for Video Summarization: Building a Bridge Between Text, Audio and Facial Cue-Based Summarization
Center for Machine Vision and Signal Analysis, Faculty of ITEE, University of Oulu, Finland(机器视觉与信号分析中心,ITEE学院,奥卢大学,芬兰);Center for Machine Vision(机器视觉与信号分析中心);Signal Analysis, Faculty of ITEE, University of Oulu, Finland(信号分析,ITEE学院,奥卢大学,芬兰)
Decomposed Opinion Summarization with Verified Aspect-Aware Modules
School of Computing and Information Systems, The University of Melbourne(墨尔本大学计算与信息系统学院);Language Technologies Institute, Carnegie Mellon University(卡内基梅隆大学语言技术研究所);School of Informatics, The University of Edinburgh(爱丁堡大学信息学院)