# Alignment Games: A Framework for Conceptual Repair in Human-AI Collaboration

arXiv: https://arxiv.org/abs/2609.35197 · HTML: https://mlsanity.com/paper/2609.35197/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 147 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces](https://mlsanity.com/paper/2309.14459/) (2023)
- [Creating General User Models from Computer Use](https://mlsanity.com/paper/2505.10831/) (2025)
- [A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration](https://mlsanity.com/paper/2404.00405/) (2024)
- [Interactive AI Alignment: Specification, Process, and Evaluation Alignment](https://mlsanity.com/paper/2311.00710/) (2023)
- [Concept Alignment](https://mlsanity.com/paper/2401.08672/) (2024)
- [Misty: UI Prototyping Through Interactive Conceptual Blending](https://mlsanity.com/paper/2409.13900/) (2024)
- [Brickify: Enabling Expressive Design Intent Specification through Direct Manipulation on Design Tokens](https://mlsanity.com/paper/2502.21219/) (2025)
- [Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships](https://mlsanity.com/paper/2407.12543/) (2024)
- [DynEx: Dynamic Code Synthesis with Structured Design Exploration for Accelerated Exploratory Programming](https://mlsanity.com/paper/2410.00400/) (2024)
- [Intent Tagging: Exploring Micro-Prompting Interactions for Supporting Granular Human-GenAI Co-Creation Workflows](https://mlsanity.com/paper/2502.18737/) (2025)
- [ChartEditor: A Human-AI Paired Tool for Authoring Pictorial Charts](https://mlsanity.com/paper/2501.07320/) (2025)
- [Semantic network analysis of abstract and concrete word associations](https://mlsanity.com/paper/2110.09096/) (2021)

## Abstract (arXiv)

The meaning of a concept in use is shaped by the situation, task, goals, and prior knowledge. For example, a request to make a poster "visually appealing for a five-year-old" might evoke bright colors and cartoon imagery for one collaborator, but less text, bold shapes, and visual simplicity for another. We call such task-relevant differences conceptual misalignment. We introduce Alignment Games, a framework for making these differences visible and repairable during human-AI interaction. Drawing on theories of situated conceptualization, we characterize task-specific conceptual frames in terms of relevant attributes, values, relations, constraints, and priorities. We then define alignment moves that intervene on the situation, the reasoning used to interpret it, or the resulting frame. Through examples from educational content generation, creative coding, and argumentative writing, we show how these moves can be composed into repair sequences and derive design principles for supporting task-sufficient conceptual alignment at runtime.