About
Research & Development
AI Breakthrough: Detecting Eviction Risks in Patient Records
TLDR: This research introduces SynthEHR-Eviction, a new pipeline that uses large language models (LLMs), human input, and automated prompt optimization to extract eviction statuses...
Research & Development
Objectomaly: Enhancing AI’s Ability to Detect the Unexpected on the Road
TLDR: Objectomaly is a new AI framework that improves the detection of unexpected objects (Out-of-Distribution) in images, crucial for autonomous driving. It refines initial...
Research & Development
Unpacking LLM Hallucinations: A Look at Computational Limits
TLDR: A research paper by Varin Sikka and Vishal Sikka argues that transformer-based language models (LLMs) inherently hallucinate when faced with tasks whose computational...
Research & Development
Advancing AI for Chinese Psychological Support: A New Dataset and Multi-Agent System
TLDR: Researchers have developed CPsDD, the first large-scale Chinese psychological support dialogue dataset with detailed strategy annotations, created using a novel framework combining expert...
Research & Development
Concept-Driven Verifiability for High-Dimensional AI Models
TLDR: The Neural Concept Verifier (NCV) is a novel AI framework that integrates Prover-Verifier Games with concept encodings to enable interpretable, non-linear classification in...
Research & Development
Unpacking Opinions: How Large Language Models Excel at Detecting Subjectivity in Text
TLDR: A research paper from CEA-LIST at CheckThat! 2025 demonstrates that Large Language Models (LLMs) with few-shot prompting can effectively detect subjectivity in text,...