4 papers
The Metacognitive Bottleneck: Japanese Riddles Reveal Fundamental Limits of Machine Insight and Self-Evaluation in Reasoning AI
Masaharu Mizumoto, Dat Nguyen, Zhiheng Han +6
Benchmark saturation and training-data contamination increasingly obscure whether reported gains in large language models (LLMs) reflect genuine advances in reasoning or familiarit…
Can Legislation Be Made Machine-Readable in PROLEG?
May-Myo Zin, Sabine Wehnert, Yuntao Kong +7
The anticipated positive social impact of regulatory processes requires both the accuracy and efficiency of their application. Modern artificial intelligence technologies, includin…
Overview of SCIDOCA 2025 Shared Task on Citation Prediction, Discovery, and Placement
An Dao, Vu Tran, Le-Minh Nguyen +1
We present an overview of the SCIDOCA 2025 Shared Task, which focuses on citation discovery and prediction in scientific documents. The task is divided into three subtasks: (1) Cit…
Multimodal Contrastive In-Context Learning
Yosuke Miyanishi, Minh Le Nguyen
The rapid growth of Large Language Models (LLMs) usage has highlighted the importance of gradient-free in-context learning (ICL). However, interpreting their inner workings remains…