# End User Authoring of Personalized Content Classifiers: Comparing Example Labeling, Rule Writing, and LLM Prompting

arXiv: https://arxiv.org/abs/2409.03247 · HTML: https://mlsanity.com/paper/2409.03247/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2024.

## Built on by (most cited first, 8 of 8)

- [Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent](https://mlsanity.com/paper/2502.11267/) (2025)
- [Value Alignment of Social Media Ranking Algorithms](https://mlsanity.com/paper/2509.14434/) (2025)
- [With a Little Help From My Friends: Collective Manipulation in Risk-Controlling Recommender Systems](https://mlsanity.com/paper/2603.28476/) (2026)
- [Asking For It: Question-Answering for Predicting Rule Infractions in Online Content Moderation](https://mlsanity.com/paper/2510.06350/) (2025)
- [Agile Deliberation: Concept Deliberation for Subjective Visual Classification](https://mlsanity.com/paper/2512.10821/) (2025)
- [Can a Unimodal Language Agent Provide Preferences to Tune a Multimodal Vision-Language Model?](https://mlsanity.com/paper/2601.06424/) (2026)
- [PaperRouter-Agent: A Content-Grounded LLM Agent for Personalized Hierarchical Paper Routing](https://mlsanity.com/paper/2607.11564/) (2026)
- [Compass: Continuously Aligning Social Media Feeds via In-Situ Reflections](https://mlsanity.com/paper/2608.04274/) (2026)

## Abstract (arXiv)

Existing tools for laypeople to create personal classifiers often assume a motivated user working uninterrupted in a single, lengthy session. However, users tend to engage with social media casually, with many short sessions on an ongoing, daily basis. To make creating personal classifiers for content curation easier for such users, tools should support rapid initialization and iterative refinement. In this work, we compare three strategies -- (1) example labeling, (2) rule writing, and (3) large language model (LLM) prompting -- for end users to build personal content classifiers. From an experiment with 37 non-programmers tasked with creating personalized moderation filters, we found that participants preferred different initializing strategies in different contexts, despite LLM prompting's better performance. However, all strategies faced challenges with iterative refinement. To overcome challenges in iterating on their prompts, participants even adopted hybrid approaches such as providing examples as in-context examples or writing rule-like prompts.