Of course. What the paper is suggesting is that during training and evaluation you should reward correct answers, punish wrong answers, and treat abstentions as somewhere in between. Current benchmarks punish abstentions and wrong answers equally, therefore models that guess instead of abstaining score higher on average.
Of course. What the paper is suggesting is that during training and evaluation you should reward correct answers, punish wrong answers, and treat abstentions as somewhere in between. Current benchmarks punish abstentions and wrong answers equally, therefore models that guess instead of abstaining score higher on average.