mlsanityData to 14 Oct 2026

Interactive AI Alignment: Specification, Process, and Evaluation Alignment

arXiv 2311.00710 ↗First posted 23 Oct 2023cs.HC cs.AIcited by 22

Not on the map. Why?

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.

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

18 of 48 references.

References · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  5. 2023Let's Verify Step by Stepcited by 3,789
  6. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  7. 2020Artificial Intelligence, Values and Alignmentcited by 448
  8. 2018Scalable agent alignment via reward modeling: a research directioncited by 447
  9. 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 237
  10. 2021Alignment of Language Agentscited by 168
  11. 2017AI Safety Gridworldscited by 110
  12. 2019Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Makingcited by 109
6 more
  1. 2016Research Priorities for Robust and Beneficial Artificial Intelligencecited by 74
  2. 2023Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferencescited by 66
  3. 2023PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactionscited by 34
  4. 2023Scientists' Perspectives on the Potential for Generative AI in their Fieldscited by 22
  5. 2023The Prompt Artistscited by 21
  6. 2021Nine Potential Pitfalls when Designing Human-AI Co-Creative Systemscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 11; 2026: 6.

22 papers.

Sort:

By area:

  1. 2025LLMs Get Lost In Multi-Turn Conversationcited by 429
  2. 2024Cocoa: Co-Planning and Co-Execution with AI Agentscited by 39
  3. 2025Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentationscited by 19
  4. 2024Designing for Human-Agent Alignment: Understanding what humans want from their agentscited by 18
  5. 2025Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedbackcited by 6
  6. 2024Large Language Models Meet User Interfaces: The Case of Provisioning Feedbackcited by 4
  7. 2026AI Alignment Breaks at the Edgecited by 4
  8. 2024Beyond Prompts: Learning from Human Communication for Enhanced AI Intent Alignmentcited by 3
  9. 2025Exploring Collaborative GenAI Agents in Synchronous Group Settings: Eliciting Team Perceptions and Design Considerations for the Future of Workcited by 3
  10. 2026Overseeing Agents Without Constant Oversight: Challenges and Opportunitiescited by 3
  11. 2024HCC Is All You Need: Alignment-The Sensible Kind Anyway-Is Just Human-Centered Computingcited by 2
  12. 2025Towards Experience-Centered AI: A Framework for Integrating Lived Experience in Design and Developmentcited by 1
10 more
  1. 2025Urbanite: A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analyticscited by 1
  2. 2025DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflowcited by 1
  3. 2025A Criminology of Machinescited by 1
  4. 2025DesignerlyLoop: Forming Design Intent through Curated Reasoning for Human-LLM Alignmentcited by 1
  5. 2026Alignment-Process-Outcome: Rethinking How AIs and Humans Collaboratecited by 1
  6. 2026Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discoverycited by 1
  7. 2025PolicyPad: Collaborative Prototyping of LLM Policiescited by 0
  8. 2025MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversationscited by 0
  9. 2026Building Intelligent User Interfaces for Human-AI Alignmentcited by 0
  10. 2026Alignment Games: A Framework for Conceptual Repair in Human-AI Collaborationcited by 0