Empirical test on real news histories shows unconstrained LLM reranking amplifies conspiratorial content exposure while prompt constraints can increase ideological diversity with limited relevance cost.
Stray, Designing recommender systems to depolarize, arXiv:2107.04953 (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems
Empirical test on real news histories shows unconstrained LLM reranking amplifies conspiratorial content exposure while prompt constraints can increase ideological diversity with limited relevance cost.