-
Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation
Ielanskyi, M., Schweighofer, K., Aichberger, L. & Hochreiter, S., Jul 2025, ICLR Workshop: Quantify Uncertainty and Hallucination in Foundation Models: The Next Frontier in Reliable AI. 1 ed. 24 p.Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review
-
Improving Uncertainty Estimation through Semantically Diverse Language Generation
Aichberger, L., Schweighofer, K., Ielanskyi, M. & Hochreiter, S., Jan 2025, International Conference On Learning Representations (ICLR 2025). 1 ed. p. 42935-42959 25 p.Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review
-
Introducing an Improved Information-Theoretic Measure of Predictive Uncertainty
Schweighofer, K., Aichberger, L., Ielanskyi, M. & Hochreiter, S., 2024, 13 p. (arXiv.org).Research output: Working paper and reports › Preprint
-
On Information-Theoretic Measures of Predictive Uncertainty
Schweighofer, K., Aichberger, L., Ielanskyi, M. & Hochreiter, S., 14 Oct 2024, 39 p.Research output: Working paper and reports › Preprint
Open Access -
Rethinking Uncertainty Estimation in Natural Language Generation
Aichberger, L., Schweighofer, K. & Hochreiter, S., 2024, 19 p. (arXiv.org).Research output: Working paper and reports › Preprint
