# Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition

arXiv: https://arxiv.org/abs/2505.06325 · HTML: https://mlsanity.com/paper/2505.06325/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 50 references that are in the map.
- First posted on arXiv 9 May 2025.

## Builds on (most cited first, 17 of 17)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond](https://mlsanity.com/paper/2103.10689/) (2021)
- [Bias in Machine Learning Software: Why? How? What to do?](https://mlsanity.com/paper/2105.12195/) (2021)
- [Are Bias Mitigation Techniques for Deep Learning Effective?](https://mlsanity.com/paper/2104.00170/) (2021)
- [An Empirical Evaluation of Predicted Outcomes as Explanations in Human-AI Decision-Making](https://mlsanity.com/paper/2208.04181/) (2022)
- [User Modelling for Avoiding Overfitting in Interactive Knowledge Elicitation for Prediction](https://mlsanity.com/paper/1710.04881/) (2017)
- [Designs for Enabling Collaboration in Human-Machine Teaming via Interactive and Explainable Systems](https://mlsanity.com/paper/2406.05003/) (2024)
- [LLM-Generated Tips Rival Expert-Created Tips in Helping Students Answer Quantum-Computing Questions](https://mlsanity.com/paper/2407.17024/) (2024)
- [Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition](https://mlsanity.com/paper/2412.08507/) (2024)
- [SpaceEditing: Integrating Human Knowledge into Deep Neural Networks via Interactive Latent Space Editing](https://mlsanity.com/paper/2212.04065/) (2022)

## Built on by (most cited first, 2 of 2)

- [Exploring Human-in-the-Loop Themes in AI Application Development: An Empirical Thematic Analysis](https://mlsanity.com/paper/2603.05510/) (2026)
- [Humanwashing -- It Should Leave You Feeling Dirty](https://mlsanity.com/paper/2605.13723/) (2026)

## Abstract (arXiv)

Latent space representations are critical for understanding and improving the behavior of machine learning models, yet they often remain obscure and intricate. Understanding and exploring the latent space has the potential to contribute valuable human intuition and expertise about respective domains. In this work, we present HILL, an interactive framework allowing users to incorporate human intuition into the model training by interactively reshaping latent space representations. The modifications are infused into the model training loop via a novel approach inspired by knowledge distillation, treating the user's modifications as a teacher to guide the model in reshaping its intrinsic latent representation. The process allows the model to converge more effectively and overcome inefficiencies, as well as provide beneficial insights to the user. We evaluated HILL in a user study tasking participants to train an optimal model, closely observing the employed strategies. The results demonstrated that human-guided latent space modifications enhance model performance while maintaining generalization, yet also revealing the risks of including user biases. Our work introduces a novel human-AI interaction paradigm that infuses human intuition into model training and critically examines the impact of human intervention on training strategies and potential biases.