mlsanityData to 7 Oct 2026

Farsight: Fostering Responsible AI Awareness During AI Application Prototyping

arXiv 2402.15350 ↗First posted 23 Feb 2024cs.HC cs.AI cs.CYcited by 28

Not on the map. Why?

Abstract (arXiv)

Prompt-based interfaces for Large Language Models (LLMs) have made prototyping and building AI-powered applications easier than ever before. However, identifying potential harms that may arise from AI applications remains a challenge, particularly during prompt-based prototyping. To address this, we present Farsight, a novel in situ interactive tool that helps people identify potential harms from the AI applications they are prototyping. Based on a user's prompt, Farsight highlights news articles about relevant AI incidents and allows users to explore and edit LLM-generated use cases, stakeholders, and harms. We report design insights from a co-design study with 10 AI prototypers and findings from a user study with 42 AI prototypers. After using Farsight, AI prototypers in our user study are better able to independently identify potential harms associated with a prompt and find our tool more useful and usable than existing resources. Their qualitative feedback also highlights that Farsight encourages them to focus on end-users and think beyond immediate harms. We discuss these findings and reflect on their implications for designing AI prototyping experiences that meaningfully engage with AI harms. Farsight is publicly accessible at: https://PAIR-code.github.io/farsight.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 93 of its 218 references that are in the map. First posted on arXiv 23 Feb 2024.

Builds on

93 of 218 references.

References · 93

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  5. 2020Extracting Training Data from Large Language Modelscited by 2,144
  6. 2018Datasheets for Datasetscited by 1,371
  7. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  8. 2018Model Cards for Model Reportingcited by 1,068
  9. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  10. 2022Red Teaming Language Models with Language Modelscited by 983
  11. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  12. 2021Ethical and social risks of harm from Language Modelscited by 957
38 more
  1. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  2. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 582
  3. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  4. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  5. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 380
  6. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
  7. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  8. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 336
  9. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 320
  10. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  11. 2021Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotationscited by 306
  12. 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 265
  13. 2018Improving fairness in machine learning systems: What do industry practitioners need?cited by 262
  14. 2019InterpretML: A Unified Framework for Machine Learning Interpretabilitycited by 243
  15. 2022Predictability and Surprise in Large Generative Modelscited by 209
  16. 2019The What-If Tool: Interactive Probing of Machine Learning Modelscited by 207
  17. 2019A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cyclecited by 192
  18. 2021Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasetscited by 179
  19. 2021Challenges in Detoxifying Language Modelscited by 169
  20. 2023Model evaluation for extreme riskscited by 167
  21. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 154
  22. 2018Aequitas: A Bias and Fairness Audit Toolkitcited by 145
  23. 2022Power to the People? Opportunities and Challenges for Participatory AIcited by 137
  24. 2022Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reductioncited by 137
  25. 2023ProPILE: Probing Privacy Leakage in Large Language Modelscited by 127
  26. 2020The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Modelscited by 125
  27. 2023On the Risk of Misinformation Pollution with Large Language Modelscited by 124
  28. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 119
  29. 2022Jury Learning: Integrating Dissenting Voices into Machine Learning Modelscited by 115
  30. 2021Detoxifying Language Models Risks Marginalizing Minority Voicescited by 106
  31. 2020Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Databasecited by 95
  32. 2019FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learningcited by 93
  33. 2023The Participatory Turn in AI Design: Theoretical Foundations and the Current State of Practicecited by 86
  34. 2023Fairlearn: Assessing and Improving Fairness of AI Systemscited by 74
  35. 2020Human Factors in Model Interpretability: Industry Practices, Challenges, and Needscited by 73
  36. 2019Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizationscited by 72
  37. 2022Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identitycited by 71
  38. 2021Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Supportcited by 61

50 most cited of 93 All 93 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 14; 2026: 8.

28 papers.

Sort:

By area:

  1. 2024ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMscited by 20
  2. 2025VeriPlan: Integrating Formal Verification and LLMs into End-User Planningcited by 19
  3. 2025Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Reviewcited by 16
  4. 202550 Years of Automated Face Recognitioncited by 13
  5. 2024Beyond the Comfort Zone: Emerging Solutions to Overcome Challenges in Integrating LLMs into Software Productscited by 11
  6. 2024Particip-AI: A Democratic Surveying Framework for Anticipating Future AI Use Cases, Harms and Benefitscited by 9
  7. 2025PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teamingcited by 8
  8. 2025From Hazard Identification to Controller Design: Proactive and LLM-Supported Safety Engineering for ML-Powered Systemscited by 7
  9. 2024Exploring Empty Spaces: Human-in-the-Loop Data Augmentationcited by 6
  10. 2025AI Awarenesscited by 6
  11. 2025Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Modelscited by 6
  12. 2024Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviorscited by 5
16 more
  1. 2025Privy: Envisioning and Mitigating Privacy Risks for Consumer-facing AI Product Conceptscited by 4
  2. 2026How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?cited by 3
  3. 2024Integrating ESG and AI: A Comprehensive Responsible AI Assessment Frameworkcited by 2
  4. 2025The role of large language models in UI/UX design: A systematic literature reviewcited by 2
  5. 2025The AI Model Risk Catalog: What Developers and Researchers Miss About Real-World AI Harmscited by 2
  6. 2026Agent-Supported Foresight for AI Systemic Risks: AI Agents for Breadth, Experts for Judgmentcited by 2
  7. 2025AI LEGO: Scaffolding Cross-Functional Collaboration in Industrial Responsible AI Practices during Early Design Stagescited by 1
  8. 2025Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based Provocationscited by 1
  9. 2025Data-Prompt Co-Evolution: Growing Test Sets to Refine LLM Behaviorcited by 1
  10. 2025PolicyPad: Collaborative Prototyping of LLM Policiescited by 0
  11. 2026Promoting Critical Thinking With Domain-Specific Generative AI Provocationscited by 0
  12. 2026PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AIcited by 0
  13. 2026Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agentscited by 0
  14. 2026What We Know about Responsible AI Practices in Industry: A Half Decade of Empirical Researchcited by 0
  15. 2026Ethics Training Agents: Facilitating Group-Based Ethics Education with Role-Playing and Discussion for Ethical Reflection and Explorationcited by 0
  16. 2026Small-world Networks of Agents Brainstorm AI Risks to Support Ideationcited by 0