# On Human Intellect and Machine Failures: Troubleshooting Integrative Machine Learning Systems

arXiv: https://arxiv.org/abs/1611.08309 · HTML: https://mlsanity.com/paper/1611.08309/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2016.

## Built on by (most cited first, 18 of 18)

- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [Interactive Debugging and Steering of Multi-Agent AI Systems](https://mlsanity.com/paper/2503.02068/) (2025)
- [Collaboration Challenges in Building ML-Enabled Systems: Communication, Documentation, Engineering, and Process](https://mlsanity.com/paper/2110.10234/) (2021)
- [The future of human-AI collaboration: a taxonomy of design knowledge for hybrid intelligence systems](https://mlsanity.com/paper/2105.03354/) (2021)
- [A Meta-Summary of Challenges in Building Products with ML Components -- Collecting Experiences from 4758+ Practitioners](https://mlsanity.com/paper/2304.00078/) (2023)
- [Platform for Situated Intelligence](https://mlsanity.com/paper/2103.15975/) (2021)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Human-AI Symbiosis: A Survey of Current Approaches](https://mlsanity.com/paper/2103.09990/) (2021)
- [Machine Learning Robustness: A Primer](https://mlsanity.com/paper/2404.00897/) (2024)
- [Whose wife is it anyway? Assessing bias against same-gender relationships in machine translation](https://mlsanity.com/paper/2401.04972/) (2024)
- [Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems](https://mlsanity.com/paper/2103.11766/) (2021)
- [Feature Interactions on Steroids: On the Composition of ML Models](https://mlsanity.com/paper/2105.06449/) (2021)
- [A Mental-Model Centric Landscape of Human-AI Symbiosis](https://mlsanity.com/paper/2202.09447/) (2022)
- [Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness](https://mlsanity.com/paper/2403.14641/) (2024)
- [Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications](https://mlsanity.com/paper/2603.15676/) (2026)
- [Understanding the Complexity and Its Impact on Testing in ML-Enabled Systems](https://mlsanity.com/paper/2301.03837/) (2023)
- [Exploring End-to-end Differentiable Neural Charged Particle Tracking -- A Loss Landscape Perspective](https://mlsanity.com/paper/2407.13420/) (2024)
- [ThuRunel: Dynamic Decoupling for Structured Advisory Dialogue](https://mlsanity.com/paper/2609.36340/) (2026)

## Abstract (arXiv)

We study the problem of troubleshooting machine learning systems that rely on analytical pipelines of distinct components. Understanding and fixing errors that arise in such integrative systems is difficult as failures can occur at multiple points in the execution workflow. Moreover, errors can propagate, become amplified or be suppressed, making blame assignment difficult. We propose a human-in-the-loop methodology which leverages human intellect for troubleshooting system failures. The approach simulates potential component fixes through human computation tasks and measures the expected improvements in the holistic behavior of the system. The method provides guidance to designers about how they can best improve the system. We demonstrate the effectiveness of the approach on an automated image captioning system that has been pressed into real-world use.