# Language-Based User Profiles for Recommendation

arXiv: https://arxiv.org/abs/2402.15623 · HTML: https://mlsanity.com/paper/2402.15623/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 23 Feb 2024.

## Builds on (most cited first, 7 of 7)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [PALR: Personalization Aware LLMs for Recommendation](https://mlsanity.com/paper/2305.07622/) (2023)
- [Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences](https://mlsanity.com/paper/2307.14225/) (2023)
- [CTRL: Connect Collaborative and Language Model for CTR Prediction](https://mlsanity.com/paper/2306.02841/) (2023)

## Built on by (most cited first, 18 of 18)

- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [TravelAgent: An AI Assistant for Personalized Travel Planning](https://mlsanity.com/paper/2409.08069/) (2024)
- [AI PERSONA: Towards Life-long Personalization of LLMs](https://mlsanity.com/paper/2412.13103/) (2024)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms](https://mlsanity.com/paper/2504.16420/) (2025)
- [PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization](https://mlsanity.com/paper/2506.12915/) (2025)
- [End-to-end Training for Recommendation with Language-based User Profiles](https://mlsanity.com/paper/2410.18870/) (2024)
- [MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs](https://mlsanity.com/paper/2510.14629/) (2025)
- [POPI: Personalizing LLMs via Optimized Natural Language Preference Inference](https://mlsanity.com/paper/2510.17881/) (2025)
- [Human Tool: An MCP-Style Framework for Human-Agent Collaboration](https://mlsanity.com/paper/2602.12953/) (2026)
- [Large Language Models, and LLM-Based Agents, Should Be Used to Enhance the Digital Public Sphere](https://mlsanity.com/paper/2410.12123/) (2024)
- [Music Recommendation with Large Language Models: Challenges, Opportunities, and Evaluation](https://mlsanity.com/paper/2511.16478/) (2025)
- [Large Language Model Driven Recommendation](https://mlsanity.com/paper/2408.10946/) (2024)
- [Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenders](https://mlsanity.com/paper/2510.08930/) (2025)
- [SteerEval: A Framework for Evaluating Steerability with Natural Language Profiles for Recommendation](https://mlsanity.com/paper/2601.21105/) (2026)
- [Bridging Textual Profiles and Latent User Embeddings for Personalization](https://mlsanity.com/paper/2605.06981/) (2026)
- [Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale](https://mlsanity.com/paper/2609.35285/) (2026)
- [A Controlled Audit of Personal AI Memory for Rating Prediction](https://mlsanity.com/paper/2610.02764/) (2026)

## Abstract (arXiv)

Most conventional recommendation methods (e.g., matrix factorization) represent user profiles as high-dimensional vectors. Unfortunately, these vectors lack interpretability and steerability, and often perform poorly in cold-start settings. To address these shortcomings, we explore the use of user profiles that are represented as human-readable text. We propose the Language-based Factorization Model (LFM), which is essentially an encoder/decoder model where both the encoder and the decoder are large language models (LLMs). The encoder LLM generates a compact natural-language profile of the user's interests from the user's rating history. The decoder LLM uses this summary profile to complete predictive downstream tasks. We evaluate our LFM approach on the MovieLens dataset, comparing it against matrix factorization and an LLM model that directly predicts from the user's rating history. In cold-start settings, we find that our method can have higher accuracy than matrix factorization. Furthermore, we find that generating a compact and human-readable summary often performs comparably with or better than direct LLM prediction, while enjoying better interpretability and shorter model input length. Our results motivate a number of future research directions and potential improvements.