purplecat: A painting of Alan Turing (General:AI)
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.
purplecat: An open book with a quill pen and a lamp. (General:Academia)
I was going over my early LJ posts and regretting that I don't post about science much any more. Science blogging requires a fair bit of mental energy to put everything together in a coherent, yet understandable, way.

Anyway, here is a paper in which I, another Computer Scientist and a legal scholar discuss what kind of explanations offered by autonomous and AI systems might be of interest to lawyers. This includes both explanations that might be offered to lawyers after some event, but also what lawyers might want to know about explanations offered to users during some interaction that let to an event. It's fairly preliminary work aimed at mapping the space more than offering specific conclusions or calls to action.

Profile

purplecat: Hand Drawn picture of a Toy Cat (Default)
purplecat

August 2025

S M T W T F S
     1 2
3 4 5678 9
10111213141516
17181920212223
24252627282930
31      

Syndicate

RSS Atom

Tags

Style Credit

Expand Cut Tags

No cut tags