# Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems

arXiv: https://arxiv.org/abs/2511.18024 · HTML: https://mlsanity.com/paper/2511.18024/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 22 Nov 2025.

## Builds on (most cited first, 13 of 13)

- [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)
- [Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control](https://mlsanity.com/paper/2405.08366/) (2024)
- [Interpreting CLIP with Hierarchical Sparse Autoencoders](https://mlsanity.com/paper/2502.20578/) (2025)
- [Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02104/) (2024)
- [A Survey on Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2308.01118/) (2023)
- [PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems](https://mlsanity.com/paper/1911.08378/) (2019)
- [Item Recommendation from Implicit Feedback](https://mlsanity.com/paper/2101.08769/) (2021)
- [Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness](https://mlsanity.com/paper/2410.21331/) (2024)
- [Neural Attentive Multiview Machines](https://mlsanity.com/paper/2002.07696/) (2020)
- [Cold Item Integration in Deep Hybrid Recommenders via Tunable Stochastic Gates](https://mlsanity.com/paper/2112.07615/) (2021)
- [Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations](https://mlsanity.com/paper/2409.14399/) (2024)
- [Unleashing the Potential of Two-Tower Models: Diffusion-Based Cross-Interaction for Large-Scale Matching](https://mlsanity.com/paper/2502.20687/) (2025)

## Built on by (most cited first, 1 of 1)

- [ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution](https://mlsanity.com/paper/2610.04605/) (2026)

## Abstract (arXiv)

We present a method for extracting monosemantic neurons, defined as latent dimensions that align with coherent and interpretable concepts, from user and item embeddings in recommender systems. Our approach employs a Sparse Autoencoder (SAE) to reveal semantic structure within pretrained representations. In contrast to work on language models, monosemanticity in recommendation must preserve the interactions between separate user and item embeddings. To achieve this, we introduce a prediction aware training objective that backpropagates through a frozen recommender and aligns the learned latent structure with the model's user-item affinity predictions. The resulting neurons capture properties such as genre, popularity, and temporal trends, and support post hoc control operations including targeted filtering and content promotion without modifying the base model. Our method generalizes across different recommendation models and datasets, providing a practical tool for interpretable and controllable personalization. Code and evaluation resources are available at https://github.com/DeltaLabTLV/Monosemanticity4Rec.