Glass-Box: Explaining AI Decisions With Counterfactual Statements Through Conversation With a Voice-enabled Virtual Assistant

@inproceedings{Sokol2018GlassBoxEA,
  title={Glass-Box: Explaining AI Decisions With Counterfactual Statements Through Conversation With a Voice-enabled Virtual Assistant},
  author={Kacper Sokol and Peter A. Flach},
  booktitle={IJCAI},
  year={2018}
}
The prevalence of automated decision making, influencing important aspects of our lives -- e.g., school admission, job market, insurance and banking -- has resulted in increasing pressure from society and regulators to make this process more transparent and ensure its explainability, accountability and fairness. We demonstrate a prototype voice-enabled device, called Glass-Box, which users can question to understand automated decisions and identify the underlying model's biases and errors. Our… 

Figures from this paper

One Explanation Does Not Fit All The Promise of Interactive Explanations for Machine Learning Transparency.

TLDR
This paper shows how to personalise counterfactual explanations by interactively adjusting their conditional statements and extract additional explanations by asking follow-up “What if?” questions, and deliberate on the risks of allowing the explainee to freely manipulate the explanations and thereby extracting information about the underlying predictive model, which might be leveraged by malicious actors to steal or game the model.

One Explanation Does Not Fit All

TLDR
This paper discusses the promises of Interactive Machine Learning for improved transparency of black-box systems using the example of contrastive explanations—a state-of-the-art approach to Interpretable Machine Learning and shows how to personalise counterfactual explanations by interactively adjusting their conditional statements and extract additional explanations by asking follow-up “What if?” questions.

One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency

TLDR
This paper shows how to personalise counterfactual explanations by interactively adjusting their conditional statements and extract additional explanations by asking follow-up “What if?” questions, and deliberate on the risks of allowing the explainee to freely manipulate the explanations and thereby extracting information about the underlying predictive model.

Explainability Is in the Mind of the Beholder: Establishing the Foundations of Explainable Artificial Intelligence

TLDR
The philosophical and social foundations of human explainability are reviewed, and the human-centred explanatory process needed to achieve the desired level of algorithmic transparency and understanding in explainees are revisited, revisiting the much disputed trade-off between transparency and predictive power.

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

TLDR
This work conducts a systematic literature review which provides readers with a thorough and reproducible analysis of the interdisciplinary research field under study and defines a taxonomy regarding both theoretical and practical approaches to contrastive and counterfactual explanation.

Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of AI Systems

TLDR
The current concept of explainability is revised and three limitations are identified: passive explainee, narrow view on the social process, and undifferentiated assessment of understanding are identified.

The Use and Misuse of Counterfactuals in Ethical Machine Learning

TLDR
It is argued that even though counterfactuals play an essential part in some causal inferences, their use for questions of algorithmic fairness and social explanations can create more problems than they resolve.

What Would You Ask the Machine Learning Model? Identification of User Needs for Model Explanations Based on Human-Model Conversations

TLDR
This is the first study which uses a conversational system to collect the needs of human operators from the interactive and iterative dialogue explorations of a predictive model.
...

References

SHOWING 1-9 OF 9 REFERENCES

Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR

TLDR
It is suggested data controllers should offer a particular type of explanation, unconditional counterfactual explanations, to support these three aims, which describe the smallest change to the world that can be made to obtain a desirable outcome, or to arrive at the closest possible world, without needing to explain the internal logic of the system.

Counterfactual Fairness

TLDR
This paper develops a framework for modeling fairness using tools from causal inference and demonstrates the framework on a real-world problem of fair prediction of success in law school.

Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences

TLDR
From a light scan of literature, it is demonstrated that there is considerable scope to infuse more results from the social and behavioural sciences into explainable AI, and some key results from these fields that are relevant to explainableAI are presented.

"Why Should I Trust You?": Explaining the Predictions of Any Classifier

TLDR
LIME is proposed, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning aninterpretable model locally varound the prediction.

Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking

TLDR
This paper presents a technique that exploits the internals of a tree-based ensemble classifier to offer recommendations for transforming true negative instances into positively predicted ones, and demonstrates the validity of the approach using an online advertising application.

Explanation in Artificial Intelligence: Insights from the Social Sciences

The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification

TLDR
The Bayesian Case Model is presented, a general framework for Bayesian case-based reasoning (CBR) and prototype classification and clustering and subspace representation that provides quantitative benefits in interpretability while preserving classification accuracy.

Embedding Projector: Interactive Visualization and Interpretation of Embeddings

TLDR
The Embedding Projector is presented, a tool for interactive visualization and interpretation of embeddings and its applications in recommender systems, NLP, and many other applications.

Tim Miller, Piers Howe, and Liz Sonenberg. Explainable ai: Beware of inmates running the asylum

  • Advances in Neural Information Processing Systems
  • 2017