3 papers indexed here
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.
UserProxyBench, an evaluation layer over the tau-bench family, and the User Fidelity Score (UFS), which measures adherence to the benchmark's private user instructions using task-grounded rubric criteria scored independently of agent success are introduced.
A diagnosis-to-intervention pipeline for object hallucination is presented, and a controlled account of what acting on the diagnostic signal actually does is presented: it localizes intervention sites with real, non-random leverage, reported as a behavioral profile rather than a single score.
This work trains language models with GRPO on multiple-choice math problems where the correct answer is always option A, then evaluates on an unseen test set with unbiased answer positions to find reasoning-answer decoupling, which separates capability loss from a learned, transferable shortcut.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
