Anthill Inside 2019

A conference on AI and Deep Learning



Divij Joshi

Model Interpretability, Explainable AI and the Right to Information

Submitted Oct 18, 2019

Issues of ‘explainability in AI’ have emerged as an important theme in the development of machine learning and statistical modelling. Most studies look at explainability through the lens of model interpretability, in order to understand underlying machine learning models better and improve them for better optimisation. However, there is limited relevance of this understanding of interpretability to applied machine learning ‘in the wild’, that is, in their real-world applications and interactions with end-users. In the context of consequential automated decisions (particularly in administrative or governmental decisions), citizens turn to robust tools like the Right to Information, for instrumentally achieving openness and accountability of decision making systems. This poster session will attempt to locate points of tension between the three concepts of interpretability, explainability and the right to information, and will build a case for why and how machine decision making systems can incorporate elements of the right to information and due process.


Consequential machine decision making is now pervasive. Automated decisions (to different degrees of automation) are now applied in fields of welfare allocation, policing and criminal justice, finance and insurance and online content moderation, among others. Many of these tools use complex algorithmic systems, including machine learning techniques, which are conventionally difficult to interpret. Efforts toward interpretation have traditionally focused on model interpretation through explaining the ‘black box’ of algorithmic systems (for example through local linear explanations or models). However, these techniques of interpretability have limited significance where end-users are concerned, for a number of reasons, including the ability of a lay citizen to parse technical models, as well as the limited information it provides for achieving instrumental purposes of explanation (for example, the ability to use an explanation to overturn a decision). Some techniques have focused on explainability without opening the black box, including through methods like counterfactual explanations. However, limited work exists on how the non-interpretability of machine decisions impacts important constitutional concepts of due process and the right to information as well as legal mechanisms like the RTI Act which actualise these rights. The RTI Act, in particular, places positive obligations upon the state to explain certain decisions, including administrative decisions taken that impact individuals. The extent to which techniques of explainability in AI can be incorporated to ensure that the RTI remains a robust instrument for holding government systems accountable will be the focus of this session.

Speaker bio

I am a lawyer and a legal researcher, working in the field of technology policy. I have researched and written extensively on issues of internet openness and digital rights. In my role as a technology policy fellow at the Mozilla Foundation, I am focussing on creating policy for improving machine decision making systems in India.



{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hybrid access (members only)

Hosted by

Anthill Inside is a forum for conversations about risk mitigation and governance in Artificial Intelligence and Deep Learning. AI developers, researchers, startup founders, ethicists, and AI enthusiasts are encouraged to: more