14 papers
Uncertainty-based Debiasing and Unlearning for Decontamination
Guangzhi Sun, Xiao Zhan, Mark Gales
Benchmark-based evaluation is the dominant paradigm for assessing large language model (LLM) capabilities, yet data contamination inflates reported performance and undermines fair…
Cross-Lingual Transfer Learning for Speech Translation
Rao Ma, Mengjie Qian, Yassir Fathullah +3
There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of th…
Structural-Based Uncertainty in Deep Learning Across Anatomical Scales: Analysis in White Matter Lesion Segmentation
Nataliia Molchanova, Vatsal Raina, Andrey Malinin +7
This paper explores uncertainty quantification (UQ) as an indicator of the trustworthiness of automated deep-learning (DL) tools in the context of white matter lesion (WML) segment…
Efficient LLM Comparative Assessment: a Product of Experts Framework for Pairwise Comparisons
Adian Liusie, Vatsal Raina, Yassir Fathullah +1
LLM-as-a-judge approaches are a practical and effective way of assessing a range of text tasks. However, when using pairwise comparisons to rank a set of candidates, the computatio…
SkillAggregation: Reference-free LLM-Dependent Aggregation
Guangzhi Sun, Anmol Kagrecha, Potsawee Manakul +2
Large Language Models (LLMs) are increasingly used to assess NLP tasks due to their ability to generate human-like judgments. Single LLMs were used initially, however, recent work…
Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models
Vyas Raina, Mark Gales
Speech enabled foundation models, either in the form of flexible speech recognition based systems or audio-prompted large language models (LLMs), are becoming increasingly popular.…