Integral Role
Research on the "role" of various components in complex systems focuses on understanding their contributions to overall system performance and behavior. Current investigations span diverse fields, examining the impact of factors like data embedding strategies in quantum computing, prompt engineering in large language models, and architectural choices in deep learning for improved generalization and efficiency. These studies are crucial for optimizing existing systems and developing new ones, with implications ranging from enhancing AI safety and healthcare applications to improving manufacturing processes and scientific discovery.
Papers
Predicting the Intention to Interact with a Service Robot:the Role of Gaze Cues
Simone Arreghini, Gabriele Abbate, Alessandro Giusti, Antonio Paolillo
Towards Better Understanding of Cybercrime: The Role of Fine-Tuned LLMs in Translation
Veronica Valeros, Anna Širokova, Carlos Catania, Sebastian Garcia
On the Role of Summary Content Units in Text Summarization Evaluation
Marcel Nawrath, Agnieszka Nowak, Tristan Ratz, Danilo C. Walenta, Juri Opitz, Leonardo F. R. Ribeiro, João Sedoc, Daniel Deutsch, Simon Mille, Yixin Liu, Lining Zhang, Sebastian Gehrmann, Saad Mahamood, Miruna Clinciu, Khyathi Chandu, Yufang Hou
The Role of $n$-gram Smoothing in the Age of Neural Networks
Luca Malagutti, Andrius Buinovskij, Anej Svete, Clara Meister, Afra Amini, Ryan Cotterell
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data
Zeyu Jia, Alexander Rakhlin, Ayush Sekhari, Chen-Yu Wei
Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators
Yinhong Liu, Han Zhou, Zhijiang Guo, Ehsan Shareghi, Ivan Vulić, Anna Korhonen, Nigel Collier
Understanding the Functional Roles of Modelling Components in Spiking Neural Networks
Huifeng Yin, Hanle Zheng, Jiayi Mao, Siyuan Ding, Xing Liu, Mingkun Xu, Yifan Hu, Jing Pei, Lei Deng