Introduces GenAI agent framework for auditing personalization algorithms via synthetic accounts with fixed personas, applied to X post-2024 election showing amplification of toxic and right-leaning content varying by ideology.
Can LLMs mimic human-like mental accounting and behavioral biases? In Proceedings of the 25th ACM Conference on Economics and Computation (EC ’24)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Causal localization via attribution and patching identifies a temporal preference subgraph in mid-to-upper layers of Qwen3-4B-Instruct-2507, with time-horizon geometry in the residual stream and initial evidence for steering-vector control.
Scoping review of 23 papers finds fairness in multi-agent AI systems is addressed superficially without robust norms or attention to autonomy and interactions, recommending structural embedding with human oversight.
citing papers explorer
-
Temporal Preference Concepts and their Functions in a Large Language Model
Causal localization via attribution and patching identifies a temporal preference subgraph in mid-to-upper layers of Qwen3-4B-Instruct-2507, with time-horizon geometry in the residual stream and initial evidence for steering-vector control.