# Filter bubbles and affective polarization in user-personalized large language model outputs

arXiv: https://arxiv.org/abs/2311.14677 · HTML: https://mlsanity.com/paper/2311.14677/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 31 Oct 2023.

## Builds on (most cited first, 8 of 8)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT](https://mlsanity.com/paper/2302.09419/) (2023)
- [PALR: Personalization Aware LLMs for Recommendation](https://mlsanity.com/paper/2305.07622/) (2023)
- [Affective Polarization in Online Climate Change Discourse on Twitter](https://mlsanity.com/paper/2008.13051/) (2020)

## Built on by (most cited first, 6 of 6)

- [Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity](https://mlsanity.com/paper/2507.00657/) (2025)
- [When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs](https://mlsanity.com/paper/2601.11000/) (2026)
- [Simulating Filter Bubble on Short-video Recommender System with Large Language Model Agents](https://mlsanity.com/paper/2504.08742/) (2025)
- [Prioritize Economy or Climate Action? Investigating ChatGPT Response Differences Based on Inferred Political Orientation](https://mlsanity.com/paper/2511.04706/) (2025)
- [Identity-Robust Language Model Generation via Content Integrity Preservation](https://mlsanity.com/paper/2601.09141/) (2026)
- [Ideological Isolation in Online Social Networks: A Survey of Computational Definitions, Metrics, and Mitigation Strategies](https://mlsanity.com/paper/2601.07884/) (2026)

## Abstract (arXiv)

Echoing the history of search engines and social media content rankings, the advent of large language models (LLMs) has led to a push for increased personalization of model outputs to individual users. In the past, personalized recommendations and ranking systems have been linked to the development of filter bubbles (serving content that may confirm a user's existing biases) and affective polarization (strong negative sentiment towards those with differing views). In this work, we explore how prompting a leading large language model, ChatGPT-3.5, with a user's political affiliation prior to asking factual questions about public figures and organizations leads to differing results. We observe that left-leaning users tend to receive more positive statements about left-leaning political figures and media outlets, while right-leaning users see more positive statements about right-leaning entities. This pattern holds across presidential candidates, members of the U.S. Senate, and media organizations with ratings from AllSides. When qualitatively evaluating some of these outputs, there is evidence that particular facts are included or excluded based on the user's political affiliation. These results illustrate that personalizing LLMs based on user demographics carry the same risks of affective polarization and filter bubbles that have been seen in other personalized internet technologies. This ``failure mode" should be monitored closely as there are more attempts to monetize and personalize these models.