30 citations · 69 across the 15 of their papers we have counts for
4 papers · 1 filter
Where Do Apparent LLM Clinical Triage Failures Arise? Localizing the Multiple-Choice Format Effect
David Fraile Navarro, Berardino Como, Jialei Sheng +2
LLM evaluations using clinician-authored triage vignettes have reported substantial under-triage under constrained multiple-choice testing. Yet model performance on the same clinic…
Uncertainty-Aware Dynamic Knowledge Graphs for Reliable Question Answering
Yu Takahashi, Shun Takeuchi, Kexuan Xin +6
Question answering (QA) systems are increasingly deployed across domains. However, their reliability is undermined when retrieved evidence is incomplete, noisy, or uncertain. Exist…
Automatic Speech Summarisation: A Scoping Review
Dana Rezazadegan, Shlomo Berkovsky, Juan C. Quiroz +4
Speech summarisation techniques take human speech as input and then output an abridged version as text or speech. Speech summarisation has applications in many domains from informa…
Empirical Analysis of Zipf's Law, Power Law, and Lognormal Distributions in Medical Discharge Reports
Juan C Quiroz, Liliana Laranjo, Catalin Tufanaru +4
Bayesian modelling and statistical text analysis rely on informed probability priors to encourage good solutions. This paper empirically analyses whether text in medical discharge…