Large Language
Large language models (LLMs) are rapidly advancing artificial intelligence, aiming to create systems capable of understanding and generating human-like text. Current research focuses on improving efficiency (e.g., through speculative decoding), exploring their intriguing properties in multimodal contexts (combining language with vision), and applying them to diverse fields like healthcare, manufacturing, and software engineering. This work is significant because LLMs are already impacting various sectors, offering potential for improved decision-making, automation, and personalized experiences, while also raising important questions about robustness, security, and ethical implications.
Papers
TiEBe: A Benchmark for Assessing the Current Knowledge of Large Language Models
Thales Sales Almeida, Giovana Kerche Bonás, João Guilherme Alves Santos, Hugo Abonizio, Rodrigo Nogueira
A Proposed Large Language Model-Based Smart Search for Archive System
Ha Dung Nguyen, Thi-Hoang Anh Nguyen, Thanh Binh Nguyen
How Toxic Can You Get? Search-based Toxicity Testing for Large Language Models
Simone Corbo, Luca Bancale, Valeria De Gennaro, Livia Lestingi, Vincenzo Scotti, Matteo Camilli
CarbonChat: Large Language Model-Based Corporate Carbon Emission Analysis and Climate Knowledge Q&A System
Zhixuan Cao, Ming Han, Jingtao Wang, Meng Jia
Automatically Planning Optimal Parallel Strategy for Large Language Models
Zongbiao Li (1), Xiezhao Li (1), Yinghao Cui (1), Yijun Chen (1), Zhixuan Gu (1), Yuxuan Liu (1), Wenbo Zhu (1), Fei Jia (1), Ke Liu (1), Qifeng Li (1), Junyao Zhan (1), Jiangtao Zhou (1), Chenxi Zhang (1), Qike Liu (1) ((1) HUAWEI)
Extracting effective solutions hidden in large language models via generated comprehensive specialists: case studies in developing electronic devices
Hikari Tomita, Nobuhiro Nakamura, Shoichi Ishida, Toshio Kamiya, Kei Terayama