![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png)
New paper on the use of dialogue for explaining logical reasoning by computers in Dialogue Explanations for Rule-Based AI Systems. There's some fairly dense maths in there establishing properties of the system - for instance if the user and computer disagree about some fact then the system will find at least once such disagreement. To achieve this it makes a number of (patently false) simplifying assumptions about what a user might be reasoning or thinking (but you can't establish anything mathematically if you go with "who knows what the user is thinking or doing" so we fell back on "assuming the user is thinking and doing something sensible, then...").
Anyway, leaving the dense and frankly not very interesting maths aside, there is also a small example of a system implemented by my PhD student which should let you see what it does.
Anyway, leaving the dense and frankly not very interesting maths aside, there is also a small example of a system implemented by my PhD student which should let you see what it does.
(no subject)
Date: 2023-12-01 03:43 pm (UTC)