# On Natural Language User Profiles for Transparent and Scrutable Recommendation

arXiv: https://arxiv.org/abs/2205.09403 · HTML: https://mlsanity.com/paper/2205.09403/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2022.

## Built on by (most cited first, 23 of 23)

- [Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences](https://mlsanity.com/paper/2307.14225/) (2023)
- [Leveraging Large Language Models in Conversational Recommender Systems](https://mlsanity.com/paper/2305.07961/) (2023)
- [The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations](https://mlsanity.com/paper/2308.02053/) (2023)
- [Large Language Model Augmented Narrative Driven Recommendations](https://mlsanity.com/paper/2306.02250/) (2023)
- [Value Profiles for Encoding Human Variation](https://mlsanity.com/paper/2503.15484/) (2025)
- [Large Language Models for User Interest Journeys](https://mlsanity.com/paper/2305.15498/) (2023)
- [GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency](https://mlsanity.com/paper/2402.08855/) (2024)
- [Editable User Profiles for Controllable Text Recommendation](https://mlsanity.com/paper/2304.04250/) (2023)
- [End-to-end Training for Recommendation with Language-based User Profiles](https://mlsanity.com/paper/2410.18870/) (2024)
- [Query Understanding in the Age of Large Language Models](https://mlsanity.com/paper/2306.16004/) (2023)
- [Preference Discerning with LLM-Enhanced Generative Retrieval](https://mlsanity.com/paper/2412.08604/) (2024)
- [POPI: Personalizing LLMs via Optimized Natural Language Preference Inference](https://mlsanity.com/paper/2510.17881/) (2025)
- [CTRL-Rec: Controlling Recommender Systems With Natural Language](https://mlsanity.com/paper/2510.12742/) (2025)
- [ACAI for SBOs: AI Co-creation for Advertising and Inspiration for Small Business Owners](https://mlsanity.com/paper/2503.06729/) (2025)
- [KNNs of Semantic Encodings for Rating Prediction](https://mlsanity.com/paper/2302.00412/) (2023)
- [Large Language Models, and LLM-Based Agents, Should Be Used to Enhance the Digital Public Sphere](https://mlsanity.com/paper/2410.12123/) (2024)
- [When Ads Become Profiles: Uncovering the Invisible Risk of Web Advertising at Scale with LLMs](https://mlsanity.com/paper/2509.18874/) (2025)
- [Large Language Model Driven Recommendation](https://mlsanity.com/paper/2408.10946/) (2024)
- [DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning](https://mlsanity.com/paper/2509.09524/) (2025)
- [Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenders](https://mlsanity.com/paper/2510.08930/) (2025)
- [Hierarchical Multi-Persona Induction from User Behavioral Logs: Learning Evidence-Grounded and Truthful Personas](https://mlsanity.com/paper/2604.26120/) (2026)
- [Bridging Textual Profiles and Latent User Embeddings for Personalization](https://mlsanity.com/paper/2605.06981/) (2026)
- [Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces](https://mlsanity.com/paper/2608.11354/) (2026)

## Abstract (arXiv)

Natural interaction with recommendation and personalized search systems has received tremendous attention in recent years. We focus on the challenge of supporting people's understanding and control of these systems and explore a fundamentally new way of thinking about representation of knowledge in recommendation and personalization systems. Specifically, we argue that it may be both desirable and possible for algorithms that use natural language representations of users' preferences to be developed. We make the case that this could provide significantly greater transparency, as well as affordances for practical actionable interrogation of, and control over, recommendations. Moreover, we argue that such an approach, if successfully applied, may enable a major step towards systems that rely less on noisy implicit observations while increasing portability of knowledge of one's interests.