Search papers, labs, and topics across Lattice.
Existing zero-shot multimodal information extraction models struggle with real-world scenarios containing both seen and unseen categories, but this work solves it by modeling hierarchical semantic relationships in hyperbolic space and aligning semantic similarity distributions.
Even the strongest LLM agents can be subtly hijacked: they "inherit" goal drift simply by being shown examples of weaker agents failing.
LLMs struggle to understand nuanced values across languages, with accuracy dropping below 77% and varying by over 20% between languages, as revealed by the new X-Value benchmark.
Overcome Alzheimer's speech detection's data scarcity with FAL-AD, a federated learning framework that hits 91.52% accuracy by generating synthetic speech samples and aligning acoustic and textual features.
Fine-tuning LLMs on datasets filtered at the token level, rather than the sentence level, can boost performance by up to 13.7%.
Speech recognition models stumble badly on real-world street names, especially for non-English speakers, but a simple synthetic data boost can dramatically improve accuracy.
LLMs still struggle to reliably produce accurate Islamic content and citations, despite relatively strong performance, revealing a critical gap in faith-sensitive AI writing.
AI-generated feedback on student portfolios from GPT-4o and Claude-Sonnet-4 shows promise for high-stakes clinical assessments, but careful evaluation is needed to ensure accuracy and educational value.
An LLM-powered smart tutor isn't just another homework helper; it's a real-time feedback loop for instructors, revealing student struggles and enabling more effective teaching.
LLMs in gastroenterology can be made significantly safer: a new framework achieves near-human expert alignment and boosts accuracy by 8% via rejection sampling.
ChatGPT-4 slashes data extraction time in scoping reviews by 66%, but don't ditch the human reviewers just yet.
LLMs can generate plain language summaries of scientific research that are as good as human-written ones, but easier to read.
