We have 4 of 54 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Symbolic state supervision raises the 20M model's frame accuracy from 31.1% to 67.3% at the same training-data budget, suggesting that learning representations of state changes can complement scaling.
In a suite of 325K experiments on 13 agents across three types of economic decisions, it is found that 8 models systematically choose more expensive options for wealthier users when requests are identical, in which the very conditions that make a personal AI agent useful - access to personal information - enable it to...
This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. LeakyLMs is the first to demonstrate that key model and deployment details can be inferred using only token generation timing, even when interacting through remote APIs. L...
Reinforcement learning with verifiable rewards (RLVR) is deployed to make models better at reasoning tasks, but its side effect on what models will divulge is under studied. Here we show that RLVR on facts increases extraction of personally identifiable information (PII) the instruct model had already memorized. We fir...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
