Tootfinder

Knowledge Collapse in LLMs: When Fluency Survives but Facts Fail under Recursive Synthetic Training
Figarri Keisha, Zekun Wu, Ze Wang, Adriano Koshiyama, Philip Treleaven
https://arxiv.org/abs/2509.04796

Knowledge Collapse in LLMs: When Fluency Survives but Facts Fail under Recursive Synthetic Training
Large language models increasingly rely on synthetic data due to human-written content scarcity, yet recursive training on model-generated outputs leads to model collapse, a degenerative process threatening factual reliability. We define knowledge collapse as a distinct three-stage phenomenon where factual accuracy deteriorates while surface fluency persists, creating "confidently wrong" outputs that pose critical risks in accuracy-dependent domains. Through controlled experiments with recursiv…

I keep giving AI a chance, but it keeps generating bullshit no matter what I type. I’m always left searching for a human response to what should be established and reasonable responses from any knowledgeable source.
This affirms my feeling that AI tools are not knowledge bases.

R2GenKG: Hierarchical Multi-modal Knowledge Graph for LLM-based Radiology Report Generation
Futian Wang, Yuhan Qiao, Xiao Wang, Fuling Wang, Yuxiang Zhang, Dengdi Sun
https://arxiv.org/abs/2508.03426

R2GenKG: Hierarchical Multi-modal Knowledge Graph for LLM-based Radiology Report Generation
X-ray medical report generation is one of the important applications of artificial intelligence in healthcare. With the support of large foundation models, the quality of medical report generation has significantly improved. However, challenges such as hallucination and weak disease diagnostic capability still persist. In this paper, we first construct a large-scale multi-modal medical knowledge graph (termed M3KG) based on the ground truth medical report using the GPT-4o. It contains 2477 enti…

RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
Zhaoyan Gong, Juan Li, Zhiqiang Liu, Lei Liang, Huajun Chen, Wen Zhang
https://arxiv.org/abs/2509.03995

RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
Current temporal knowledge graph question answering (TKGQA) methods primarily focus on implicit temporal constraints, lacking the capability of handling more complex temporal queries, and struggle with limited reasoning abilities and error propagation in decomposition frameworks. We propose RTQA, a novel framework to address these challenges by enhancing reasoning over TKGs without requiring training. Following recursive thinking, RTQA recursively decomposes questions into sub-problems, solves …

This Week in Sports Trivia: September 4, 2025 https://www.nytimes.com/athletic/6595097/2025/09/04/this-week-in-sports-trivia-september-4-2025/

CAI Fluency: A Framework for Cybersecurity AI Fluency
V\'ictor Mayoral-Vilches, Jasmin Wachter, Crist\'obal R. J. Veas Chavez, Cathrin Schachner, Luis Javier Navarrete-Lozano, Mar\'ia Sanz-G\'omez
https://arxiv.org/abs/2508.13588

CAI Fluency: A Framework for Cybersecurity AI Fluency
This work introduces CAI Fluency, an an educational platform of the Cybersecurity AI (CAI) framework dedicated to democratizing the knowledge and application of cybersecurity AI tools in the global security community. The main objective of the CAI framework is to accelerate the widespread adoption and effective use of artificial intelligence-based cybersecurity solutions, pathing the way to vibe-hacking, the cybersecurity analogon to vibe-coding. CAI Fluency builds upon the Framework for AI F…

CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection
Qiyu Chen, Zhen Qu, Wei Luo, Haiming Yao, Yunkang Cao, Yuxin Jiang, Yinan Duan, Huiyuan Luo, Chengkan Lv, Zhengtao Zhang
https://arxiv.org/abs/2508.03447

CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection
Recently, large pre-trained vision-language models have shown remarkable performance in zero-shot anomaly detection (ZSAD). With fine-tuning on a single auxiliary dataset, the model enables cross-category anomaly detection on diverse datasets covering industrial defects and medical lesions. Compared to manually designed prompts, prompt learning eliminates the need for expert knowledge and trial-and-error. However, it still faces the following challenges: (i) static learnable tokens struggle to …

Geomorphometric atlas of ice-free Antarctic areas: Problem statement, concept, and key principles
Igor V. Florinsky
https://arxiv.org/abs/2508.02846 https://

Geomorphometric atlas of ice-free Antarctic areas: Problem statement, concept, and key principles
In this article, we rationalize the need to develop a geomorphometric atlas of ice-free Antarctic areas. Geomorphometric mapping of such landscapes is necessary to obtain new knowledge about quantitative topographic characteristics of these unique objects and the further use of morphometric information in the geosciences. First, we present a concept, structure, and content of the atlas including a list of 194 areas to be modeled and mapped. For each area, the atlas will include the following ma…

This Week in Sports Trivia: July 3, 2025 https://www.nytimes.com/athletic/6468843/2025/07/03/this-week-in-sports-trivia-july-3-2025/

A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
Ming Hu, Chenglong Ma, Wei Li, Wanghan Xu, Jiamin Wu, Jucheng Hu, Tianbin Li, Guohang Zhuang, Jiaqi Liu, Yingzhou Lu, Ying Chen, Chaoyang Zhang, Cheng Tan, Jie Ying, Guocheng Wu, Shujian Gao, Pengcheng Chen, Jiashi Lin, Haitao Wu, Lulu Chen, Fengxiang Wang, Yuanyuan Zhang, Xiangyu Zhao, Feilong Tang, Encheng Su, Junzhi Ning, Xinyao Liu, Ye Du, Changkai Ji, Cheng Tang, Huihui Xu, Ziyang Chen, Ziyan Hu…

A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the complex nature of scientific data. This survey presents a comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate. We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge, emphasizing the…