LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems

2026-06-01

AI Summary

Traditional recommender systems, overly optimized for click-through rates, tend to exacerbate exposure to extreme content in political news and intensify ideological polarization. This work proposes a lightweight large language model (LLM)-based reranking approach that employs constrained prompting to actively modulate users’ exposure to extreme or conspiratorial content while preserving recommendation relevance. The study presents the first empirical evidence that unconstrained LLM reranking amplifies the risk of extreme content amplification; however, incorporating prompt regularization significantly reduces such exposure and enhances ideological diversity, with only a marginal decline in relevance. This method offers a novel pathway toward recommender systems that balance personalization with societal values.

Abstract

Recommender systems have grown from content-organization tools into sophisticated systems that shape daily behavior. By controlling what we see, they shape what we perceive, raising concerns about filter bubbles, radicalization, polarization, and social inequality. Large language models (LLMs) enable more powerful personalization, intensifying these dynamics. Yet most recommenders are tuned for engagement or limited accuracy metrics, with little attention to broader social implications, e.g. how personalization reshapes exposure in socially consequential domains. We investigate whether LLM-assisted reranking, while improving personalization, inadvertently amplifies exposure to ideologically extreme or conspiratorial political content, a risk theorized but not empirically characterized in news recommendation. Using real news-consumption histories, we rerank YouTube's sidebar candidates through zero-shot, instruction-based prompting. We compare a baseline prompt with a constrained variant that preserves topical relevance and broadens ideological exposure while reducing conspiratorial or extreme content. Without constraints, reranking strengthened personalization but increased exposure to conspiratorial and extremist material for users whose histories contained such content. Lightweight prompt-level regularization reduced promotion of extreme content and increased ideological diversity, with modest relevance loss. Synthetic experiments suggest that LLMs rerank via statistical regularities in language rather than semantic understanding of ideology, clarifying why naive prompts amplify these patterns and why regularization can reshape them. Together, our results highlight the power of LLMs to operationalize contextual nuance in high-stakes recommendation, and the need to evaluate LLM-assisted personalization beyond accuracy and treat prompt design as a value-laden rather than neutral default.

Problem

• recommender systems
• large language models
• ideological extremism
• conspiratorial content
• personalization

Innovation

• LLM-assisted reranking
• prompt regularization
• ideological diversity
• conspiratorial content mitigation
• value-laden prompting