A reasoning and value alignment test to assess advanced gpt reasoning

TR McIntosh, T Liu, T Susnjak, P Watters… - ACM Transactions on …, 2024‏ - dl.acm.org
In response to diverse perspectives on artificial general intelligence (AGI), ranging from
potential safety and ethical concerns to more extreme views about the threats it poses to …

Supporting text entry in virtual reality with large language models

L Chen, Y Cai, R Wang, S Ding, Y Tang… - … Virtual Reality and …, 2024‏ - ieeexplore.ieee.org
Text entry in virtual reality (VR) often faces challenges in terms of efficiency and task loads.
Prior research has explored various solutions, including specialized keyboard layouts …

An energy-based model for word-level autocompletion in computer-aided translation

C Yang, G Huang, M Yu, Z Zhang, S Li… - Transactions of the …, 2024‏ - direct.mit.edu
Word-level AutoCompletion (WLAC) is a rewarding yet challenging task in Computer-aided
Translation. Existing work addresses this task through a classification model based on a …

Generative input: Towards next-generation input methods paradigm

K Ding, Y Wang, Z Xu, Z Jia, S Wang, C Liu… - ar**s in Low-Resource Scenarios
B Sun, J Li, H Zhou, F Meng, K Li… - Proceedings of the 62nd …, 2024‏ - aclanthology.org
Pinyin input method engine (IME) refers to the transformation tool from pinyin sequence to
Chinese characters, which is widely used on mobile phone applications. Due to the …

Personalized Language Model Learning on Text Data Without User Identifiers

Y Ding, Y Tan, X Liu, C Niu, F Meng, J Zhou… - arxiv preprint arxiv …, 2025‏ - arxiv.org
In many practical natural language applications, user data are highly sensitive, requiring
anonymous uploads of text data from mobile devices to the cloud without user identifiers …

Still All Greeklish to Me: Greeklish to Greek transliteration

A Toumazatos, J Pavlopoulos… - Proceedings of the …, 2024‏ - aclanthology.org
Modern Greek is normally written in the Greek alphabet. In informal online messages,
however, Greek is often written using characters available on Latin-character keyboards, a …

Explainable Neural Networks with Guarantees: A Sparse Estimation Approach

A Ledent, P Liu - arxiv preprint arxiv:2501.02010, 2025‏ - arxiv.org
Balancing predictive power and interpretability has long been a challenging research area,
particularly in powerful yet complex models like neural networks, where nonlinearity …