4 papers
Evidence-Informed LLM Beliefs for Continual Scientific Discovery
Dhruv Agarwal, Reece Adamson, Andrew McCallum +3
Open-ended scientific discovery with large language models (LLMs) increasingly operates as a long-horizon loop of hypothesis search and verification, where a reward signal guides w…
AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise
Dhruv Agarwal, Bodhisattwa Prasad Majumder, Reece Adamson +8
The promise of autonomous scientific discovery (ASD) hinges not only on answering questions, but also on knowing which questions to ask. Most recent works in ASD explore the use of…
Replicating ReLM Results: Validating Large Language Models with ReLM
Reece Adamson, Erin Song
Validating Large Language Models with ReLM explores the application of formal languages to evaluate and control Large Language Models (LLMs) for memorization, bias, and zero-shot p…
The Forward-Forward Algorithm: Characterizing Training Behavior
Reece Adamson
The Forward-Forward algorithm is an alternative learning method which consists of two forward passes rather than a forward and backward pass employed by backpropagation. Forward-Fo…