XU-RS: Explaining Credal Width in Random-Set Language Models
Quick summary
arXiv:2609.37594v1 Announce Type: new Abstract: Uncertainty estimates tell us how unsure a model is, but not why. Without knowing which parts of an input influences a model's uncertainty, we cannot tell whether that uncertainty score depends on input features that are relevant for the task. We study this problem in randomset classifiers built using pretrained language models. These classifiers assign probability to individual answers and to groups of answers, producing lower and upper probabilities for each answer; The difference between these probabilities, called credal width, is used to rep
Key takeaways
- arXiv:2609.37594v1 Announce Type: new Abstract: Uncertainty estimates tell us how unsure a model is, but not why.
- Without knowing which parts of an input influences a model's uncertainty, we cannot tell whether that uncertainty score depends on input features that are relevant for the task.
- We study this problem in randomset classifiers built using pretrained language models.
Why it matters
The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.
Member comments