# Eliciting Model Steering Interactions from Users via Data and Visual Design Probes

arXiv: https://arxiv.org/abs/2310.09314 · HTML: https://mlsanity.com/paper/2310.09314/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 86 references that are in the map.
- First posted on arXiv 12 Oct 2023.

## Builds on (most cited first, 25 of 25)

- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Improving fairness in machine learning systems: What do industry practitioners need?](https://mlsanity.com/paper/1812.05239/) (2018)
- [Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy](https://mlsanity.com/paper/2002.04087/) (2020)
- [Jury Learning: Integrating Dissenting Voices into Machine Learning Models](https://mlsanity.com/paper/2202.02950/) (2022)
- [Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research](https://mlsanity.com/paper/2112.01716/) (2021)
- [Human-AI Collaboration in Data Science: Exploring Data Scientists' Perceptions of Automated AI](https://mlsanity.com/paper/1909.02309/) (2019)
- [AutoML to Date and Beyond: Challenges and Opportunities](https://mlsanity.com/paper/2010.10777/) (2020)
- [A Survey of Visual Analytics Techniques for Machine Learning](https://mlsanity.com/paper/2008.09632/) (2020)
- [Whose Ground Truth? Accounting for Individual and Collective Identities Underlying Dataset Annotation](https://mlsanity.com/paper/2112.04554/) (2021)
- [Human-in-the-loop Artificial Intelligence](https://mlsanity.com/paper/1710.08191/) (2017)
- [The future of human-AI collaboration: a taxonomy of design knowledge for hybrid intelligence systems](https://mlsanity.com/paper/2105.03354/) (2021)
- [The State of the Art in Integrating Machine Learning into Visual Analytics](https://mlsanity.com/paper/1802.07954/) (2018)
- [Visual Interaction with Deep Learning Models through Collaborative Semantic Inference](https://mlsanity.com/paper/1907.10739/) (2019)
- [Whither AutoML? Understanding the Role of Automation in Machine Learning Workflows](https://mlsanity.com/paper/2101.04834/) (2021)
- [Fits and Starts: Enterprise Use of AutoML and the Role of Humans in the Loop](https://mlsanity.com/paper/2101.04296/) (2021)
- [Towards A Process Model for Co-Creating AI Experiences](https://mlsanity.com/paper/2104.07595/) (2021)
- [Recent Research Advances on Interactive Machine Learning](https://mlsanity.com/paper/1811.04548/) (2018)
- [Surfacing Visualization Mirages](https://mlsanity.com/paper/2001.02316/) (2020)
- [GenNI: Human-AI Collaboration for Data-Backed Text Generation](https://mlsanity.com/paper/2110.10185/) (2021)
- [A Bayesian Cognition Approach to Improve Data Visualization](https://mlsanity.com/paper/1901.02949/) (2019)
- [Speculative Execution for Guided Visual Analytics](https://mlsanity.com/paper/1908.02627/) (2019)
- [Bayesian-Assisted Inference from Visualized Data](https://mlsanity.com/paper/2008.00142/) (2020)
- [Investigating Direct Manipulation of Graphical Encodings as a Method for User Interaction](https://mlsanity.com/paper/1908.00679/) (2019)
- [User Ex Machina : Simulation as a Design Probe in Human-in-the-Loop Text Analytics](https://mlsanity.com/paper/2101.02244/) (2021)

## Abstract (arXiv)

Domain experts increasingly use automated data science tools to incorporate machine learning (ML) models in their work but struggle to "debug" these models when they are incorrect. For these experts, semantic interactions can provide an accessible avenue to guide and refine ML models without having to programmatically dive into its technical details. In this research, we conduct an elicitation study using data and visual design probes to examine if and how experts with a spectrum of ML expertise use semantic interactions to update a simple classification model. We use our design probes to facilitate an interactive dialogue with 20 participants and codify their interactions as a set of target-interaction pairs. Interestingly, our findings revealed that many targets of semantic interactions do not directly map to ML model parameters, but instead aim to augment the data a model uses for training. We also identify reasons that participants would hesitate to interact with ML models, including burdens of cognitive load and concerns of injecting bias. Unexpectedly participants also saw the value of using semantic interactions to work collaboratively with members of their team. Participants with less ML expertise found this to be a useful mechanism for communicating their concerns to ML experts. This was an especially important observation, as our study also shows the different needs that correspond to diverse ML expertise. Collectively, we demonstrate that design probes are effective tools for proactively gathering the affordances that should be offered in an interactive machine learning system.