BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Xiang Yin (Imperial College London)
DTSTART:20251023T180000Z
DTEND:20251023T190000Z
DTSTAMP:20260423T021311Z
UID:OLS/192
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/OLS/192/">On
  explaining Quantitative Bipolar Argumentation Frameworks</a>\nby Xiang Yi
 n (Imperial College London) as part of Online logic seminar\n\n\nAbstract\
 nQuantitative Bipolar Argumentation Frameworks (QBAFs) provide a powerful 
 tool for modeling reasoning in various applications such as recommender sy
 stems and fraud detection. However\, there is limited work on explaining t
 heir numerical reasoning outcomes in a systematic way. In this talk\, I wi
 ll present three novel explanation methods tailored for QBAFs. First\, Arg
 ument Attribution Explanations (AAEs) quantify how much each argument cont
 ributes to a given outcome. Second\, Relation Attribution Explanations (RA
 Es) shift the focus from explaining the influence of arguments to the supp
 ort and attack relations\, offering a more fine-grained view of the reason
 ing process. Third\, Counterfactual Explanations (CEs) identify changes to
  the base scores of the arguments that would lead to a different but more 
 desired outcome\, supporting actionable insights and contestability.\n
LOCATION:https://researchseminars.org/talk/OLS/192/
END:VEVENT
END:VCALENDAR