4 papers
Efficiently Aligning Language Models with Online Natural Language Feedback
Christine Ye, Joe Benton
Reinforcement learning with verifiable rewards has been used to elicit impressive performance from language models in many domains. But, broadly beneficial deployments of AI may re…
ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?
Christine Ye, Sihan Yuan, Suchetha Cooray +10
Frontier AI agents show increasing promise as scientific research assistants, and may eventually be useful for extended, open-ended research workflows. However, in order to use age…
Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
Nevan Wichers, Aram Ebtekar, Ariana Azarbal +8
Large language models are sometimes trained with imperfect oversight signals, leading to undesired behaviors such as reward hacking and sycophancy. Improving oversight quality can…
Generative AI for Overall Mission Effectiveness at the Habitable Worlds Observatory
Megan Shabram, Ryan McClelland, John Wu +14
Here we present several use cases for using Generative AI (Gen AI) to improve systems engineering and cognitive knowledge management related to the future of astronomy from a culmi…