Interrogating the Black Box: Transparency through Information-Seeking Dialogues

02/09/2021
by   Andrea Aler Tubella, et al.
18

This paper is preoccupied with the following question: given a (possibly opaque) learning system, how can we understand whether its behaviour adheres to governance constraints? The answer can be quite simple: we just need to "ask" the system about it. We propose to construct an investigator agent to query a learning agent – the suspect agent – to investigate its adherence to a given ethical policy in the context of an information-seeking dialogue, modeled in formal argumentation settings. This formal dialogue framework is the main contribution of this paper. Through it, we break down compliance checking mechanisms into three modular components, each of which can be tailored to various needs in a vast amount of ways: an investigator agent, a suspect agent, and an acceptance protocol determining whether the responses of the suspect agent comply with the policy. This acceptance protocol presents a fundamentally different approach to aggregation: rather than using quantitative methods to deal with the non-determinism of a learning system, we leverage the use of argumentation semantics to investigate the notion of properties holding consistently. Overall, we argue that the introduced formal dialogue framework opens many avenues both in the area of compliance checking and in the analysis of properties of opaque systems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/26/2018

Optimization of Information-Seeking Dialogue Strategy for Argumentation-Based Dialogue System

Argumentation-based dialogue systems, which can handle and exchange argu...
research
04/26/2021

Relational Argumentation Semantics

In this paper, we propose a fresh perspective on argumentation semantics...
research
04/14/2022

Stateless and Rule-Based Verification For Compliance Checking Applications

Underlying computational model has an important role in any computation....
research
11/28/2022

Towards Preserving Semantic Structure in Argumentative Multi-Agent via Abstract Interpretation

Over the recent twenty years, argumentation has received considerable at...
research
05/30/2022

Theme Aspect Argumentation Model for Handling Fallacies

In this paper, we present a novel approach to identify fallacies through...
research
07/27/2021

A Storytelling Robot managing Persuasive and Ethical Stances via ACT-R: an Exploratory Study

We present a storytelling robot, controlled via the ACT-R cognitive arch...

Please sign up or login with your details

Forgot password? Click here to reset