To Predict or Not to Predict? Towards Reliable Uncertainty Estimation in the Presence of Noise

Nouran Khallaf, Serge Sharoff


Abstract
This study examines the role of uncertainty estimation (UE) methods in multilingual text classification under noisy and non-topical conditions. Using a complex-vs-simple sentence classification task across several languages, we evaluate a range of UE techniques against a range of metrics to assess their quality. Results indicate that while methods relying on softmax outputs remain competitive in high-resource in-domain settings, their reliability declines in low-resource or domain-shift scenarios. In contrast, Monte Carlo dropout approaches demonstrate consistently strong performance across all languages, offering more robust calibration, stable decision thresholds, and greater discriminative power even under adverse conditions. We further demonstrate the positive impact of UE on non-topical classification: selectively abstaining from predicting the 10% most uncertain instances increases the macro F1 score from 0.81 to 0.85 in the Readme task. By integrating UE with trustworthiness metrics, this study provides actionable insights for developing more reliable NLP systems in real-world multilingual environments.
Anthology ID:
2026.lrec-1.11
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
152–168
Language:
External URL:
https://lrec.elra.info/lrec2026-main-011
DOI:
10.63317/5ecb4bj2cv4v
Bibkey:
Cite (ACL):
Nouran Khallaf and Serge Sharoff. 2026. To Predict or Not to Predict? Towards Reliable Uncertainty Estimation in the Presence of Noise. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 152–168, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
To Predict or Not to Predict? Towards Reliable Uncertainty Estimation in the Presence of Noise (Khallaf & Sharoff, LREC 2026)
Copy Citation: