3 papers
cs.CL2025
Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
Erik Jones, Arjun Patrawala, Jacob Steinhardt
Humans often rely on subjective natural language to direct language models (LLMs); for example, users might instruct the LLM to write an enthusiastic blogpost, while developers mig…
cs.CR2024
Adversaries Can Misuse Combinations of Safe Models
Erik Jones, Anca Dragan, Jacob Steinhardt
Developers try to evaluate whether an AI system can be misused by adversaries before releasing it; for example, they might test whether a model enables cyberoffense, user manipulat…
cs.LG2024
Feedback Loops With Language Models Drive In-Context Reward Hacking
Alexander Pan, Erik Jones, Meena Jagadeesan +1
Language models influence the external world: they query APIs that read and write to web pages, generate content that shapes human behavior, and run system commands as autonomous a…