Lens methods inspect model computation by mapping intermediate activations to vocabulary tokens. Yet the concepts humans need to read out often span multiple tokens---entities, phrases, intermediate objects---making token-level readouts incomplete. Reliable multi-token readout with little model-specific preparation rem...
As LLMs increasingly act as delegated agents, they are expected to protect principals'interests when interacting with external parties. Standard alignment objectives, such as helpfulness, harmlessness, and honesty, do not specify how agents should protect principals'strategic interests under delegation. We formalize Ag...
Zi-Meng Huang, Shi-Lei Chen, Jia-Tong Zhao et al.· 1 citation
This work constructs the missing supervision through a psychologically grounded agent simulation framework, and distil it into a parameter-efficient evaluator that predicts click-through intent, together with the three companion dimensions of ad quality, as smooth, differentiable estimates.
John L. Turner-Smith, Zimeng Huang, Yuhan Fu et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
