News
Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning
arXiv:2412.08587v2 Announce Type: replace Abstract: Both encoder-only models (e.g., BERT, RoBERTa) and large language models...
Adopting agentic AI? Build AI fluency, redesign workflows, don’t neglect supervision
How can organizations decide how to use human-in-the-loop mechanisms and collaborative frameworks with AI agents?Read...
Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning
arXiv:2505.09738v1 Announce Type: new Abstract: Pretrained language models (LLMs) are often constrained by their fixed...
A Unified Representation for Continuity and Discontinuity: Syntactic and Computational Motivations
arXiv:2506.05686v1 Announce Type: new Abstract: This paper advances a unified representation of linguistic structure for...
A Survey on (M)LLM-Based GUI Agents
arXiv:2504.13865v2 Announce Type: replace-cross Abstract: Graphical User Interface (GUI) Agents have emerged as a transformative...
A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification
arXiv:2504.18884v2 Announce Type: replace Abstract: With the advance of large language models (LLMs), LLMs have...
A new atomic clock in space could help us measure elevations on Earth
In 2003, engineers from Germany and Switzerland began building a bridge across the Rhine River...
A long-abandoned US nuclear technology is making a comeback in China
China has once again beat everyone else to a clean energy milestone—its new nuclear reactor...
A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment
arXiv:2502.13520v2 Announce Type: replace Abstract: This paper introduces the Balanced Arabic Readability Evaluation Corpus (BAREC)...
A Gentle Introduction to Word Embedding and Text Vectorization
“I’m feeling blue today” versus “I painted the fence blue...
A Gentle Introduction to Multi-Head Attention and Grouped-Query Attention
This post is divided into three parts; they are: • Why Attention is Needed •...
A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage
arXiv:2504.21035v2 Announce Type: replace-cross Abstract: Sanitizing sensitive text data typically involves removing personally identifiable information...
