# Supporting Co-Adaptive Machine Teaching through Human Concept Learning and Cognitive Theories

arXiv: https://arxiv.org/abs/2409.16561 · HTML: https://mlsanity.com/paper/2409.16561/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2024.

## Built on by (most cited first, 4 of 4)

- [Unequal Opportunities: Examining the Bias in Geographical Recommendations by Large Language Models](https://mlsanity.com/paper/2504.05325/) (2025)
- [DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition](https://mlsanity.com/paper/2507.18802/) (2025)
- [Does AI Coaching Prepare us for Workplace Negotiations?](https://mlsanity.com/paper/2509.22545/) (2025)
- [Generate, Evaluate, Iterate: Synthetic Data for Human-in-the-Loop Refinement of LLM Judges](https://mlsanity.com/paper/2511.04478/) (2025)

## Abstract (arXiv)

An important challenge in interactive machine learning, particularly in subjective or ambiguous domains, is fostering bi-directional alignment between humans and models. Users teach models their concept definition through data labeling, while refining their own understandings throughout the process. To facilitate this, we introduce MOCHA, an interactive machine learning tool informed by two theories of human concept learning and cognition. First, it utilizes a neuro-symbolic pipeline to support Variation Theory-based counterfactual data generation. By asking users to annotate counterexamples that are syntactically and semantically similar to already-annotated data but predicted to have different labels, the system can learn more effectively while helping users understand the model and reflect on their own label definitions. Second, MOCHA uses Structural Alignment Theory to present groups of counterexamples, helping users comprehend alignable differences between data items and annotate them in batch. We validated MOCHA's effectiveness and usability through a lab study with 18 participants.