TourMart quantifies commission steering in LLM travel agents via paired counterfactual prompts, reporting 3.5-7.7 percentage point increases in steered recommendations for tested models.
Friedman, Eli Lucherini, Jonathan Mayer, Marshini Chetty, and Arvind Narayanan
11 Pith papers cite this work, alongside 514 external citations. Polarity classification is still indexing.
11
Pith papers citing it
514
external citations · Crossref
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Agentic browsers are vulnerable to 20 web and LLM attacks with 18 implemented, exposing five failure modes across four major LLM models that require redesign before safe deployment.
Privy uses LLMs to extract privacy rights from policies and deliver interactive guidance, reaching 0.979 precision and completing 96.3% of tasks in 3.2 steps on average across 14 sites.
ConsentDiff enables longitudinal tracking of privacy policy churn and consent UI patterns, finding ongoing changes, shifts away from high-friction banners, and higher policy-UI alignment when rejection options are visible.
New benchmark Scammer4U finds 54-93% critical PII leakage from frontier web agents on scam sites versus 0% on benign twins, plus a 30-point gap between verbalized suspicion and actual submission.
Interviews with 12 privacy-advocating UI/UX designers reveal how personal values, team negotiations, and business pressures shape their efforts to implement privacy beyond legal minimums.
GreenZ is a conceptual three-layer sustainable UX framework built on ten principles, five operational systems, and practical tools, centered on an eight-type Digital Waste Taxonomy and a model questioning AI necessity before implementation.
Users' memory of privacy settings drifts over time from exact recall to gist-based impressions that bias toward sharing with larger audiences than originally intended.
Committing to explicit meaning via a domain-grounded vocabulary of individuals, actions, facts, and concepts improves software usability, enables modular LLM code generation, and supports accountable agent behavior.
WCAG guidelines flag three deceptive patterns—countdown timers, auto-play, and hidden information—as violations, providing a legal and design route to limit manipulative interfaces.
Deception in generative AI is subtle and normalized through defaults and interactions, with users often complicit, calling for friction, awareness, and regulatory approaches to protect users.
citing papers explorer
-
TourMart: A Parametric Audit Instrument for Commission Steering in LLM Travel Agents
TourMart quantifies commission steering in LLM travel agents via paired counterfactual prompts, reporting 3.5-7.7 percentage point increases in steered recommendations for tested models.