LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems

• URL: http://arxiv.org/abs/2606.02883v1
• Date: Mon, 01 Jun 2026 20:54:14 GMT
• Title: LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems
• Abstract summary: Large language models (LLMs) enable more powerful personalization.<n>We investigate whether LLM-assisted reranking inadvertently amplifies exposure to ideologically extreme or conspiratorial political content.
• Score: 0.612477318852572
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Inference-Time Mitigation of Adversarial Political Bias in Large Language Models [11.657742684742258]
  We present different methods to shield Large Language Models (LLMs) against the injection of political bias.<n>Our results demonstrate that the proposed Recursive Self-Correction approach raises model performance from a Political Neutrality Likert scale baseline of 2.14 to 4.56.
  arXiv  Detail & Related papers  (2026-07-24T01:52:10Z)
• Enhancing Sequential Recommendation with World Knowledge from Large Language Models [35.436916487752285]
  GRASP is a flexible framework that integrates generation augmented retrieval for synthesis and similarity retrieval.<n>The retrieved similar users/items serve as auxiliary contextual information for the later holistic attention enhancement module.<n>GraSP consistently achieves state-of-the-art performance when integrated with diverse backbones.
  arXiv  Detail & Related papers  (2025-11-25T10:59:38Z)
• The Right to Be Remembered: Preserving Maximally Truthful Digital Memory in the Age of AI [3.527046810232699]
  Large language models (LLMs) can amplify the effect by collapsing multiple perspectives into one answer.<n>Certain narratives, individuals or groups, may be disproportionately suppressed, while others are disproportionately elevated.<n>This paper presents a concept of the Right To Be Remembered (RTBR) which encompasses minimizing the risk of AI-driven information omission.
  arXiv  Detail & Related papers  (2025-10-17T20:38:12Z)
• Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts [79.1081247754018]
  Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks.<n>We propose a framework based on Contact Searching Questions(CSQ) to quantify the likelihood of deception.
  arXiv  Detail & Related papers  (2025-08-08T14:46:35Z)
• Probing Association Biases in LLM Moderation Over-Sensitivity [42.191744175730726]
  Large Language Models are widely used for content moderation but often misclassify benign comments as toxic.<n>We introduce Topic Association Analysis, a semantic-level approach to quantify how LLMs associate certain topics with toxicity.<n>More advanced models (e.g., GPT-4 Turbo) demonstrate stronger topic stereotype despite lower overall false positive rates.
  arXiv  Detail & Related papers  (2025-05-29T18:07:48Z)
• Simulating Filter Bubble on Short-video Recommender System with Large Language Model Agents [24.570722028960844]
  This paper uses a large language model-based simulation framework to shed light on the dynamics between recommendation algorithms and user feedback.<n>We identify critical factors, such as demographic features and category attraction that exacerbate content homogenization.<n>We propose safeguards to promote equity for vulnerable groups, such as women and low-income populations.
  arXiv  Detail & Related papers  (2025-03-23T10:35:58Z)
• Persuasion with Large Language Models: a Survey [49.86930318312291]
  Large Language Models (LLMs) have created new disruptive possibilities for persuasive communication. In areas such as politics, marketing, public health, e-commerce, and charitable giving, such LLM Systems have already achieved human-level or even super-human persuasiveness. Our survey suggests that the current and future potential of LLM-based persuasion poses profound ethical and societal risks.
  arXiv  Detail & Related papers  (2024-11-11T10:05:52Z)
• OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models [68.17018458283651]
  This work focuses on the offline evaluation of the chain-of-thought capabilities of LLMs. We use knowledge graphs (e.g., Wikidata5m) to provide feedback on the generated chain of thoughts. We show how to optimize LLMs based on the proposed evaluation method.
  arXiv  Detail & Related papers  (2024-10-31T07:48:44Z)
• Cognitive Biases in Large Language Models for News Recommendation [68.90354828533535]
  This paper explores the potential impact of cognitive biases on large language models (LLMs) based news recommender systems. We discuss strategies to mitigate these biases through data augmentation, prompt engineering and learning algorithms aspects.
  arXiv  Detail & Related papers  (2024-10-03T18:42:07Z)
• Whose Side Are You On? Investigating the Political Stance of Large Language Models [56.883423489203786]
  We investigate the political orientation of Large Language Models (LLMs) across a spectrum of eight polarizing topics. Our investigation delves into the political alignment of LLMs across a spectrum of eight polarizing topics, spanning from abortion to LGBTQ issues. The findings suggest that users should be mindful when crafting queries, and exercise caution in selecting neutral prompt language.
  arXiv  Detail & Related papers  (2024-03-15T04:02:24Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• Improving Factual Consistency of News Summarization by Contrastive Preference Optimization [65.11227166319546]
  Large language models (LLMs) generate summaries that are factually inconsistent with original articles.<n>These hallucinations are challenging to detect through traditional methods.<n>We propose Contrastive Preference Optimization (CPO) to disentangle the LLMs' propensities to generate faithful and fake content.
  arXiv  Detail & Related papers  (2023-10-30T08:40:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.