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.
On the conversational per- suasiveness of GPT-4
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
extension 1
other 1
citation-polarity summary
representative citing papers
A 30-token prompt requesting a neutral comparison table cuts sponsored recommendations in LLMs from roughly 50% to near zero.
The authors introduce Agentivism as a learning theory for human-AI interaction that explains how durable capability develops through selective delegation, epistemic monitoring, reconstructive internalization, and transfer under reduced support.
Debiasing-DPO reduces bias to spurious social contexts by 84% and improves predictive accuracy by 52% on average for LLMs evaluating U.S. classroom transcripts.
Adversarial explanation attacks preserve nearly all human trust in wrong AI outputs by using persuasive framing, shown in a study varying reasoning, evidence, style, and format with over 200 participants.
Zero-shot LLM agents with human personas predict individual social media reactions better than chance (MCC 0.29) but worse than conventional text classifiers (MCC 0.36).
LLM narrative explanations of varying persuasiveness did not improve human decision accuracy over AI predictions alone but increased reliance on AI even when incorrect.
A survey-experiment with 236 participants shows most believe myths about gig worker vulnerabilities and that targeted counterarguments can reduce those beliefs.
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.
-
Just Ask for a Table: A Thirty-Token User Prompt Defeats Sponsored Recommendations in Twelve LLMs
A 30-token prompt requesting a neutral comparison table cuts sponsored recommendations in LLMs from roughly 50% to near zero.
-
Agentivism: a learning theory for the age of artificial intelligence
The authors introduce Agentivism as a learning theory for human-AI interaction that explains how durable capability develops through selective delegation, epistemic monitoring, reconstructive internalization, and transfer under reduced support.
-
Mitigating LLM biases toward spurious social contexts using direct preference optimization
Debiasing-DPO reduces bias to spurious social contexts by 84% and improves predictive accuracy by 52% on average for LLMs evaluating U.S. classroom transcripts.
-
When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making
Adversarial explanation attacks preserve nearly all human trust in wrong AI outputs by using persuasive framing, shown in a study varying reasoning, evidence, style, and format with over 200 participants.
-
LLM Agents Predict Social Media Reactions but Do Not Outperform Text Classifiers: Benchmarking Simulation Accuracy Using 120K+ Personas of 1511 Humans
Zero-shot LLM agents with human personas predict individual social media reactions better than chance (MCC 0.29) but worse than conventional text classifiers (MCC 0.36).
-
Human Decision-Making with Persuasive and Narrative LLM Explanations
LLM narrative explanations of varying persuasiveness did not improve human decision accuracy over AI predictions alone but increased reliance on AI even when incorrect.
-
Understanding, Challenging, and Demystifying Perceptions of Gig Worker Vulnerabilities
A survey-experiment with 236 participants shows most believe myths about gig worker vulnerabilities and that targeted counterarguments can reduce those beliefs.