mlsanityData to 7 Oct 2026

The System Model and the User Model: Exploring AI Dashboard Design

arXiv 2305.02469 ↗First posted 4 May 2023cs.HC cs.AI cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

This is a speculative essay on interface design and artificial intelligence. Recently there has been a surge of attention to chatbots based on large language models, including widely reported unsavory interactions. We contend that part of the problem is that text is not all you need: sophisticated AI systems should have dashboards, just like all other complicated devices. Assuming the hypothesis that AI systems based on neural networks will contain interpretable models of aspects of the world around them, we discuss what data such dashboards might display. We conjecture that, for many systems, the two most important models will be of the user and of the system itself. We call these the System Model and User Model. We argue that, for usability and safety, interfaces to dialogue-based AI systems should have a parallel display based on the state of the System Model and the User Model. Finding ways to identify, interpret, and display these two models should be a core part of interface research for AI.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 18 of its 40 references that are in the map. First posted on arXiv 4 May 2023.

Builds on

18 of 40 references.

References · 18

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  3. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  4. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  5. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,046
  6. 2022In-context Learning and Induction Headscited by 930
  7. 2022Toy Models of Superpositioncited by 928
  8. 2021Probing Classifiers: Promises, Shortcomings, and Advancescited by 831
  9. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  10. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 417
  11. 2020Understanding the Role of Individual Units in a Deep Neural Networkcited by 254
  12. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 217
6 more
  1. 2019Visualizing and Measuring the Geometry of BERTcited by 215
  2. 2021Implicit Representations of Meaning in Neural Language Modelscited by 179
  3. 2023A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operationscited by 141
  4. 2022Language Models as Agent Modelscited by 131
  5. 2021Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Colorcited by 118
  6. 2020Finding Universal Grammatical Relations in Multilingual BERTcited by 108

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 4; 2026: 2.

12 papers.

  1. 2024LatentQA: Teaching LLMs to Decode Activations Into Natural Languagecited by 49
  2. 2024Designing a Dashboard for Transparency and Control of Conversational AIcited by 43
  3. 2024Who's asking? User personas and the mechanics of latent misalignmentcited by 40
  4. 2024Monitoring Latent World States in Language Models with Propositional Probescited by 39
  5. 2024Towards interactive evaluations for interaction harms in human-AI systemscited by 27
  6. 2025Training Language Models to Explain Their Own Computationscited by 27
  7. 2024Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertaintycited by 23
  8. 2026Language Model Circuits Are Sparse in the Neuron Basiscited by 18
  9. 2025What Does it Mean for a Neural Network to Learn a "World Model"?cited by 7
  10. 2025Caught in the Act: a mechanistic approach to detecting deceptioncited by 6
  11. 2026Verbalizing LLMs' assumptions to explain and control sycophancycited by 3
  12. 2025Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AIcited by 2