How certain is your Transformer?

A Shelmanov, E Tsymbalov, D Puzyrev… - Proceedings of the …, 2021 - aclanthology.org
In this work, we consider the problem of uncertainty estimation for Transformer-based
models. We investigate the applicability of uncertainty estimates based on dropout usage at …

Uncertainty-aware reliable text classification

Y Hu, L Khan - Proceedings of the 27th ACM SIGKDD Conference on …, 2021 - dl.acm.org
Deep neural networks have significantly contributed to the success in predictive accuracy for
classification tasks. However, they tend to make over-confident predictions in real-world …

LM-polygraph: Uncertainty estimation for language models

E Fadeeva, R Vashurin, A Tsvigun… - arxiv preprint arxiv …, 2023 - arxiv.org
Recent advancements in the capabilities of large language models (LLMs) have paved the
way for a myriad of groundbreaking applications in various fields. However, a significant …

Clur: Uncertainty estimation for few-shot text classification with contrastive learning

J He, X Zhang, S Lei, A Alhamadani, F Chen… - Proceedings of the 29th …, 2023 - dl.acm.org
Few-shot text classification has extensive application where the sample collection is
expensive or complicated. When the penalty for classification errors is high, such as early …

Towards more accurate uncertainty estimation in text classification

J He, X Zhang, S Lei, Z Chen, F Chen… - Proceedings of the …, 2020 - aclanthology.org
The uncertainty measurement of classified results is especially important in areas requiring
limited human resources for higher accuracy. For instance, data-driven algorithms …