# Unexpected Knowledge: Auditing Wikipedia and Grokipedia Search Recommendations

arXiv: https://arxiv.org/abs/2512.17027 · HTML: https://mlsanity.com/paper/2512.17027/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Builds on (most cited first, 15 of 15)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Relevance meets Diversity: A User-Centric Framework for Knowledge Exploration through Recommendations](https://mlsanity.com/paper/2408.03772/) (2024)
- [Efficient Neural Query Auto Completion](https://mlsanity.com/paper/2008.02879/) (2020)
- [Trie-NLG: Trie Context Augmentation to Improve Personalized Query Auto-Completion for Short and Unseen Prefixes](https://mlsanity.com/paper/2307.15455/) (2023)
- [Algorithmic Drift: A Simulation Framework to Study the Effects of Recommender Systems on User Preferences](https://mlsanity.com/paper/2409.16478/) (2024)
- [Intent Models for Contextualising and Diversifying Query Suggestions](https://mlsanity.com/paper/1312.1611/) (2013)
- [Personalized Query Auto-Completion Through a Lightweight Representation of the User Context](https://mlsanity.com/paper/1905.01386/) (2019)
- [What did Elon change? A comprehensive analysis of Grokipedia](https://mlsanity.com/paper/2511.09685/) (2025)
- [Imitate TheWorld: A Search Engine Simulation Platform](https://mlsanity.com/paper/2107.07693/) (2021)
- [Learning to Navigate Wikipedia by Taking Random Walks](https://mlsanity.com/paper/2211.00177/) (2022)
- [Epistemic Substitution: How Grokipedia's AI-Generated Encyclopedia Restructures Authority](https://mlsanity.com/paper/2512.03337/) (2025)
- [Going Down the Rabbit Hole: Characterizing the Long Tail of Wikipedia Reading Sessions](https://mlsanity.com/paper/2203.06932/) (2022)
- [Curious Rhythms: Temporal Regularities of Wikipedia Consumption](https://mlsanity.com/paper/2305.09497/) (2023)
- [Random Surfers on a Web Encyclopedia](https://mlsanity.com/paper/1507.04489/) (2015)
- [Open Access Improves the Dissemination of Science: Insights from Wikipedia](https://mlsanity.com/paper/2305.13945/) (2023)

## Built on by (most cited first, 2 of 2)

- [Harm in AI-Driven Societies: An Audit of Toxicity Adoption on Chirper.ai](https://mlsanity.com/paper/2601.01090/) (2026)
- [Is Grokipedia Right-Leaning? Comparing Political Framing in Wikipedia and Grokipedia on Controversial Topics](https://mlsanity.com/paper/2601.15484/) (2026)

## Abstract (arXiv)

Encyclopedic knowledge platforms are key gateways through which users explore information online. The recent release of Grokipedia, a fully AI-generated encyclopedia, introduces a new alternative to traditional, well-established platforms like Wikipedia. In this context, search engine mechanisms play an important role in guiding users exploratory paths, yet their behavior across different encyclopedic systems remains underexplored. In this work, we address this gap by providing the first comparative analysis of search engine in Wikipedia and Grokipedia. Using nearly 10,000 neutral English words and their substrings as queries, we collect over 70,000 search engine results and examine their semantic alignment, overlap, and topical structure. We find that both platforms frequently generate results that are weakly related to the original query and, in many cases, surface unexpected content starting from innocuous queries. Despite these shared properties, the two systems often produce substantially different recommendation sets for the same query. Through topical annotation and trajectory analysis, we further identify systematic differences in how content categories are surfaced and how search engine results evolve over multiple stages of exploration. Overall, our findings show that unexpected search engine outcomes are a common feature of both the platforms, even though they exhibit discrepancies in terms of topical distribution and query suggestions.