Search Results for author:
Found 10 papers, 6 papers with code
LLMs achieve adult human performance on higher-order theory of mind tasks
This paper builds on prior work by introducing a handwritten test suite -- Multi-Order Theory of Mind Q&A -- and using it to compare the performance of five LLMs to a newly gathered adult human benchmark.
Can LLMs get help from other LLMs without revealing private information?
In this work, we show the feasibility of applying cascade systems in such setups by equipping the local model with privacy-preserving techniques that reduce the risk of leaking private information when querying the remote model.
Social Learning: Towards Collaborative Learning with Large Language Models
We present and evaluate two approaches for knowledge transfer between LLMs.
Towards Generalist Biomedical AI
While considerable work is needed to validate these models in real-world use cases, our results represent a milestone towards the development of generalist biomedical AI systems.
Towards Expert-Level Medical Question Answering with Large Language Models
Large language models (LLMs) have catalyzed significant progress in medical question answering; Med-PaLM was the first model to exceed a "passing" score in US Medical Licensing Examination (USMLE) style questions with a score of 67. 2% on the MedQA dataset.
Large Language Models Encode Clinical Knowledge
To resolve this we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars.
Ranked #4 on
Multiple Choice Question Answering (MCQA)
on MedMCQA
(Dev Set (Acc-%) metric)
UIBert: Learning Generic Multimodal Representations for UI Understanding
Our key intuition is that the heterogeneous features in a UI are self-aligned, i. e., the image and text features of UI components, are predictive of each other.
A Field Guide to Federated Optimization
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection.
Meta-Learning Bidirectional Update Rules
We show that classical gradient-based backpropagation in neural networks can be seen as a special case of a two-state network where one state is used for activations and another for gradients, with update rules derived from the chain rule.
Generative Models for Effective ML on Private, Decentralized Datasets
To improve real-world applications of machine learning, experienced modelers develop intuition about their datasets, their models, and how the two interact.
