About
Research & Development
Unpacking Numerical Confounding: How LLMs Process Intertwined Numbers
TLDR: This research paper investigates how Large Language Models (LLMs) internally represent and integrate multiple numerical attributes of an entity, and how irrelevant numerical...
Research & Development
Bridging LLMs and Knowledge Graphs for Smarter Question Answering
TLDR: The LLM–KGFR framework combines large language models (LLMs) with a Knowledge Graph Foundation Retriever (KGFR) to overcome LLM limitations in knowledge-intensive tasks. KGFR...
Research & Development
Advancing AI Agents: Introducing GUI-360 for Desktop Tasks
TLDR: GUI-360 is a new, large-scale dataset and benchmark designed to improve computer-using agents (CUAs) that automate tasks on desktop environments like Windows Office...
Research & Development
RxSafeBench: A New Benchmark to Assess AI’s Medication Safety in Healthcare
TLDR: A new research paper introduces RxSafeBench, the first comprehensive benchmark designed to evaluate Large Language Models (LLMs) on medication safety in simulated clinical...
Research & Development
Enhancing LLMs for Smarter Decisions: A Regret-Minimization Training Approach
TLDR: Researchers developed Iterative Regret-Minimization Fine-Tuning (Iterative RMFT), a new post-training method that improves LLMs' decision-making abilities. It works by having LLMs generate decision...
Applications & Use Cases
OnCue: Gaming-Inspired Keyboard for Parkinson’s Patients Secures 2025 James Dyson Award
TLDR: Alessandra Galli's 'OnCue' keyboard, designed to assist individuals with Parkinson's disease through AI-powered predictive text and haptic feedback, has won the medical category...