# Interactive AI Alignment: Specification, Process, and Evaluation Alignment

arXiv: https://arxiv.org/abs/2311.00710 · HTML: https://mlsanity.com/paper/2311.00710/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 48 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Scalable agent alignment via reward modeling: a research direction](https://mlsanity.com/paper/1811.07871/) (2018)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Alignment of Language Agents](https://mlsanity.com/paper/2103.14659/) (2021)
- [AI Safety Gridworlds](https://mlsanity.com/paper/1711.09883/) (2017)
- [Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Making](https://mlsanity.com/paper/1902.02960/) (2019)
- [Research Priorities for Robust and Beneficial Artificial Intelligence](https://mlsanity.com/paper/1602.03506/) (2016)
- [Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences](https://mlsanity.com/paper/2307.14225/) (2023)
- [PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactions](https://mlsanity.com/paper/2308.05184/) (2023)
- [Scientists' Perspectives on the Potential for Generative AI in their Fields](https://mlsanity.com/paper/2304.01420/) (2023)
- [The Prompt Artists](https://mlsanity.com/paper/2303.12253/) (2023)
- [Nine Potential Pitfalls when Designing Human-AI Co-Creative Systems](https://mlsanity.com/paper/2104.00358/) (2021)

## Built on by (most cited first, 22 of 22)

- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [Cocoa: Co-Planning and Co-Execution with AI Agents](https://mlsanity.com/paper/2412.10999/) (2024)
- [Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations](https://mlsanity.com/paper/2509.11062/) (2025)
- [Designing for Human-Agent Alignment: Understanding what humans want from their agents](https://mlsanity.com/paper/2404.04289/) (2024)
- [Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedback](https://mlsanity.com/paper/2511.10032/) (2025)
- [Large Language Models Meet User Interfaces: The Case of Provisioning Feedback](https://mlsanity.com/paper/2404.11072/) (2024)
- [AI Alignment Breaks at the Edge](https://mlsanity.com/paper/2602.20042/) (2026)
- [Beyond Prompts: Learning from Human Communication for Enhanced AI Intent Alignment](https://mlsanity.com/paper/2405.05678/) (2024)
- [Exploring Collaborative GenAI Agents in Synchronous Group Settings: Eliciting Team Perceptions and Design Considerations for the Future of Work](https://mlsanity.com/paper/2504.14779/) (2025)
- [Overseeing Agents Without Constant Oversight: Challenges and Opportunities](https://mlsanity.com/paper/2602.16844/) (2026)
- [HCC Is All You Need: Alignment-The Sensible Kind Anyway-Is Just Human-Centered Computing](https://mlsanity.com/paper/2405.03699/) (2024)
- [Towards Experience-Centered AI: A Framework for Integrating Lived Experience in Design and Development](https://mlsanity.com/paper/2508.06849/) (2025)
- [Urbanite: A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analytics](https://mlsanity.com/paper/2508.07390/) (2025)
- [DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow](https://mlsanity.com/paper/2509.12626/) (2025)
- [A Criminology of Machines](https://mlsanity.com/paper/2511.02895/) (2025)
- [DesignerlyLoop: Forming Design Intent through Curated Reasoning for Human-LLM Alignment](https://mlsanity.com/paper/2511.15331/) (2025)
- [Alignment-Process-Outcome: Rethinking How AIs and Humans Collaborate](https://mlsanity.com/paper/2603.08017/) (2026)
- [Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery](https://mlsanity.com/paper/2605.05921/) (2026)
- [PolicyPad: Collaborative Prototyping of LLM Policies](https://mlsanity.com/paper/2509.19680/) (2025)
- [MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations](https://mlsanity.com/paper/2512.13154/) (2025)
- [Building Intelligent User Interfaces for Human-AI Alignment](https://mlsanity.com/paper/2602.11753/) (2026)
- [Alignment Games: A Framework for Conceptual Repair in Human-AI Collaboration](https://mlsanity.com/paper/2609.35197/) (2026)

## Abstract (arXiv)

Modern AI enables a high-level, declarative form of interaction: Users describe the intended outcome they wish an AI to produce, but do not actually create the outcome themselves. In contrast, in traditional user interfaces, users invoke specific operations to create the desired outcome. This paper revisits the basic input-output interaction cycle in light of this declarative style of interaction, and connects concepts in AI alignment to define three objectives for interactive alignment of AI: specification alignment (aligning on what to do), process alignment (aligning on how to do it), and evaluation alignment (assisting users in verifying and understanding what was produced). Using existing systems as examples, we show how these user-centered views of AI alignment can be used descriptively, prescriptively, and as an evaluative aid.