About
Research & Development
A New AI-Powered Pipeline for Transparent and Efficient Full-Text Screening in Systematic Reviews
TLDR: The paper introduces an auditable pipeline for full-text screening in systematic reviews, combining contrastive semantic highlighting, Mamdani fuzzy logic, and LLM judgment. This...
Research & Development
Unmasking Hidden Biases: How LLMs Infer Demographics from Disability Cues
TLDR: A new study reveals that Large Language Models (LLMs) frequently make biased demographic inferences based on disability-related language in user queries. The research,...
Research & Development
Automating NLP Model Design for Morphologically Rich Languages with MorphNAS
TLDR: MorphNAS is a new differentiable neural architecture search framework that enhances DARTS by incorporating linguistic features to automatically design optimal neural networks for...
Research & Development
Exploring Model Adaptability for Short Answer Grading Across Diverse Datasets
TLDR: This research investigates whether AI models trained on existing datasets can be effectively used for new, unexplored datasets, specifically in automated short answer...
Research & Development
Unseen Threats: Protecting AI’s Reasoning from Cognitive Attacks
TLDR: A new research paper by Yuksel AYDIN introduces cognitive cybersecurity, a discipline focused on protecting AI reasoning processes from adversarial manipulation. It highlights...
Research & Development
Enhancing ASR Reliability: A Framework for Internal Consistency Across Semantic and Structural Levels
TLDR: The MGSC framework improves end-to-end ASR robustness in noisy environments by enforcing internal self-consistency at both macro-level sentence semantics and micro-level token alignment....