# TEARS: Textual Representations for Scrutable Recommendations

arXiv: https://arxiv.org/abs/2410.19302 · HTML: https://mlsanity.com/paper/2410.19302/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 62 references that are in the map.
- First posted on arXiv 25 Oct 2024.

## Builds on (most cited first, 29 of 29)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [Large Language Models as Zero-Shot Conversational Recommenders](https://mlsanity.com/paper/2308.10053/) (2023)
- [How to Index Item IDs for Recommendation Foundation Models](https://mlsanity.com/paper/2305.06569/) (2023)
- [Embarrassingly Shallow Autoencoders for Sparse Data](https://mlsanity.com/paper/1905.03375/) (2019)
- [Joint Deep Modeling of Users and Items Using Reviews for Recommendation](https://mlsanity.com/paper/1701.04783/) (2017)
- [Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences](https://mlsanity.com/paper/2307.14225/) (2023)
- [Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2108.10539/) (2021)
- [VIP5: Towards Multimodal Foundation Models for Recommendation](https://mlsanity.com/paper/2305.14302/) (2023)
- [Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?](https://mlsanity.com/paper/2401.13544/) (2024)
- [Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation](https://mlsanity.com/paper/2401.13870/) (2024)
- [Transparent and Scrutable Recommendations Using Natural Language User Profiles](https://mlsanity.com/paper/2402.05810/) (2024)
- [Explainable Recommendation with Personalized Review Retrieval and Aspect Learning](https://mlsanity.com/paper/2306.12657/) (2023)
- [Large Language Models are Not Stable Recommender Systems](https://mlsanity.com/paper/2312.15746/) (2023)
- [End-to-end Training for Recommendation with Language-based User Profiles](https://mlsanity.com/paper/2410.18870/) (2024)
- [Recommendations by Concise User Profiles from Review Text](https://mlsanity.com/paper/2311.01314/) (2023)
- [A Comprehensive Overview of Recommender System and Sentiment Analysis](https://mlsanity.com/paper/2109.08794/) (2021)
- [KNNs of Semantic Encodings for Rating Prediction](https://mlsanity.com/paper/2302.00412/) (2023)

## Built on by (most cited first, 5 of 5)

- [Interactive Recommendation Agent with Active User Commands](https://mlsanity.com/paper/2509.21317/) (2025)
- [CTRL-Rec: Controlling Recommender Systems With Natural Language](https://mlsanity.com/paper/2510.12742/) (2025)
- [High Fidelity Textual User Representation over Heterogeneous Sources via Reinforcement Learning](https://mlsanity.com/paper/2602.07333/) (2026)
- [SteerEval: A Framework for Evaluating Steerability with Natural Language Profiles for Recommendation](https://mlsanity.com/paper/2601.21105/) (2026)
- [Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale](https://mlsanity.com/paper/2609.35285/) (2026)

## Abstract (arXiv)

Traditional recommender systems rely on high-dimensional (latent) embeddings for modeling user-item interactions, often resulting in opaque representations that lack interpretability. Moreover, these systems offer limited control to users over their recommendations. Inspired by recent work, we introduce TExtuAl Representations for Scrutable recommendations (TEARS) to address these challenges. Instead of representing a user's interests through a latent embedding, TEARS encodes them in natural text, providing transparency and allowing users to edit them. To do so, TEARS uses a modern LLM to generate user summaries based on user preferences. We find the summaries capture user preferences uniquely. Using these summaries, we take a hybrid approach where we use an optimal transport procedure to align the summaries' representation with the learned representation of a standard VAE for collaborative filtering. We find this approach can surpass the performance of three popular VAE models while providing user-controllable recommendations. We also analyze the controllability of TEARS through three simulated user tasks to evaluate the effectiveness of a user editing its summary.