12 citations · 16 across the 6 of their papers we have counts for
4 papers · 1 filter
Welcome to the Age of Agent Ads: Using On-Policy Attacks to Steer Agentic Decisions
Tim R. Davidson, Marija Šakota, Joshua Joseph +1
People increasingly delegate option-ranking tasks (e.g., shopping, job search, travel) to AI agents, which creates incentives to steer agentic decisions via "agent ads." To defend…
The Future of Facts: Tracing the Factual Generation-Verification Gap
Tim R. Davidson, Anja Surina, Caglar Gulcehre
Language models are becoming the default interface to factual knowledge, yet they often verify outputs more reliably than they generate them. This generation-verification gap (GV-g…
Self-Recognition in Language Models
Tim R. Davidson, Viacheslav Surkov, Veniamin Veselovsky +3
A rapidly growing number of applications rely on a small set of closed-source language models (LMs). This dependency might introduce novel security risks if LMs develop self-recogn…
Evaluating Language Model Agency through Negotiations
Tim R. Davidson, Veniamin Veselovsky, Martin Josifoski +4
We introduce an approach to evaluate language model (LM) agency using negotiation games. This approach better reflects real-world use cases and addresses some of the shortcomings o…